{"updated":"2026-10-14","license":"CC BY 4.0","source":"https://onpremworld.com","docs":"https://onpremworld.com/openapi.json","count":37,"items":[{"id":"llama-3.1-8b","name":"Llama 3.1 8B Instruct","family":"Llama 3.1","developer":"Meta","releaseDate":"2024-07","license":{"name":"Llama 3.1 Community License","commercial":true},"architecture":"dense","totalParamsB":8,"activeParamsB":8,"maxContextTokens":131072,"ollamaTag":"llama3.1:8b","huggingFaceRepo":"meta-llama/Llama-3.1-8B-Instruct","sources":{"releaseDate":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/MODEL_CARD.md","license":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE","totalParamsB":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/MODEL_CARD.md","activeParamsB":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/MODEL_CARD.md","numLayers":"https://huggingface.co/RedHatAI/Llama-3.1-8B-Instruct/resolve/main/config.json","numKvHeads":"https://huggingface.co/RedHatAI/Llama-3.1-8B-Instruct/resolve/main/config.json","headDim":"https://huggingface.co/RedHatAI/Llama-3.1-8B-Instruct/resolve/main/config.json","hiddenSize":"https://huggingface.co/RedHatAI/Llama-3.1-8B-Instruct/resolve/main/config.json","maxContextTokens":"https://huggingface.co/RedHatAI/Llama-3.1-8B-Instruct/resolve/main/config.json","modalities":"https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct","huggingFaceRepo":"https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct","attention":"https://huggingface.co/RedHatAI/Llama-3.1-8B-Instruct/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/meta-llama/Llama-3.1-8B-Instruct?expand[]=safetensors","ollamaTag":"https://ollama.com/library/llama3.1/tags"},"url":{"en":"https://onpremworld.com/en/models/llama-3.1-8b","zh-tw":"https://onpremworld.com/zh-tw/models/llama-3.1-8b"}},{"id":"llama-3.2-3b","name":"Llama 3.2 3B Instruct","family":"Llama 3.2","developer":"Meta","releaseDate":"2024-09","license":{"name":"Llama 3.2 Community License","commercial":true},"architecture":"dense","totalParamsB":3.21,"activeParamsB":3.21,"maxContextTokens":131072,"ollamaTag":"llama3.2:3b","huggingFaceRepo":"meta-llama/Llama-3.2-3B-Instruct","sources":{"releaseDate":"https://ai.meta.com/blog/llama-3-2-connect-2024-vision-edge-mobile-devices/","license":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE","totalParamsB":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/MODEL_CARD.md","activeParamsB":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/MODEL_CARD.md","numLayers":"https://huggingface.co/unsloth/Llama-3.2-3B-Instruct/resolve/main/config.json","numKvHeads":"https://huggingface.co/unsloth/Llama-3.2-3B-Instruct/resolve/main/config.json","headDim":"https://huggingface.co/unsloth/Llama-3.2-3B-Instruct/resolve/main/config.json","hiddenSize":"https://huggingface.co/unsloth/Llama-3.2-3B-Instruct/resolve/main/config.json","maxContextTokens":"https://huggingface.co/unsloth/Llama-3.2-3B-Instruct/resolve/main/config.json","modalities":"https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct","huggingFaceRepo":"https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct","attention":"https://huggingface.co/unsloth/Llama-3.2-3B-Instruct/resolve/main/config.json","architectureCrossCheck":"https://ollama.com/library/llama3.2:3b/blobs/dde5aa3fc5ff","checkpointParamsB":"https://huggingface.co/api/models/meta-llama/Llama-3.2-3B-Instruct?expand[]=safetensors","ollamaTag":"https://ollama.com/library/llama3.2/tags"},"url":{"en":"https://onpremworld.com/en/models/llama-3.2-3b","zh-tw":"https://onpremworld.com/zh-tw/models/llama-3.2-3b"}},{"id":"llama-3.3-70b","name":"Llama 3.3 70B Instruct","family":"Llama 3.3","developer":"Meta","releaseDate":"2024-12","license":{"name":"Llama 3.3 Community License","commercial":true},"architecture":"dense","totalParamsB":70,"activeParamsB":70,"maxContextTokens":131072,"ollamaTag":"llama3.3:70b","huggingFaceRepo":"meta-llama/Llama-3.3-70B-Instruct","sources":{"releaseDate":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/MODEL_CARD.md","license":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/LICENSE","totalParamsB":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/MODEL_CARD.md","activeParamsB":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/MODEL_CARD.md","numLayers":"https://huggingface.co/RedHatAI/Llama-3.3-70B-Instruct/resolve/main/config.json","numKvHeads":"https://huggingface.co/RedHatAI/Llama-3.3-70B-Instruct/resolve/main/config.json","headDim":"https://huggingface.co/RedHatAI/Llama-3.3-70B-Instruct/resolve/main/config.json","hiddenSize":"https://huggingface.co/RedHatAI/Llama-3.3-70B-Instruct/resolve/main/config.json","maxContextTokens":"https://huggingface.co/RedHatAI/Llama-3.3-70B-Instruct/resolve/main/config.json","modalities":"https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct","huggingFaceRepo":"https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct","attention":"https://huggingface.co/RedHatAI/Llama-3.3-70B-Instruct/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/meta-llama/Llama-3.3-70B-Instruct?expand[]=safetensors","ollamaTag":"https://ollama.com/library/llama3.3/tags"},"url":{"en":"https://onpremworld.com/en/models/llama-3.3-70b","zh-tw":"https://onpremworld.com/zh-tw/models/llama-3.3-70b"}},{"id":"llama-4-scout","name":"Llama 4 Scout 17B-16E Instruct","family":"Llama 4","developer":"Meta","releaseDate":"2025-04","license":{"name":"Llama 4 Community License","commercial":true},"architecture":"moe","totalParamsB":109,"activeParamsB":17,"maxContextTokens":10485760,"ollamaTag":"llama4:16x17b","huggingFaceRepo":"meta-llama/Llama-4-Scout-17B-16E-Instruct","sources":{"releaseDate":"https://github.com/meta-llama/llama-models/blob/main/models/llama4/MODEL_CARD.md","license":"https://github.com/meta-llama/llama-models/blob/main/models/llama4/LICENSE","totalParamsB":"https://github.com/meta-llama/llama-models/blob/main/models/llama4/MODEL_CARD.md","activeParamsB":"https://github.com/meta-llama/llama-models/blob/main/models/llama4/MODEL_CARD.md","numLayers":"https://huggingface.co/RedHatAI/Llama-4-Scout-17B-16E-Instruct/resolve/main/config.json","numKvHeads":"https://huggingface.co/RedHatAI/Llama-4-Scout-17B-16E-Instruct/resolve/main/config.json","headDim":"https://huggingface.co/RedHatAI/Llama-4-Scout-17B-16E-Instruct/resolve/main/config.json","hiddenSize":"https://huggingface.co/RedHatAI/Llama-4-Scout-17B-16E-Instruct/resolve/main/config.json","maxContextTokens":"https://huggingface.co/RedHatAI/Llama-4-Scout-17B-16E-Instruct/resolve/main/config.json","modalities":"https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct","huggingFaceRepo":"https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct","attention":"https://huggingface.co/RedHatAI/Llama-4-Scout-17B-16E-Instruct/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/meta-llama/Llama-4-Scout-17B-16E-Instruct?expand[]=safetensors","ollamaTag":"https://ollama.com/library/llama4/tags"},"url":{"en":"https://onpremworld.com/en/models/llama-4-scout","zh-tw":"https://onpremworld.com/zh-tw/models/llama-4-scout"}},{"id":"qwen3-8b","name":"Qwen3-8B","family":"Qwen3","developer":"Alibaba Qwen","releaseDate":"2025-04","license":{"name":"Apache-2.0","commercial":true},"architecture":"dense","totalParamsB":8.2,"activeParamsB":8.2,"maxContextTokens":32768,"ollamaTag":"qwen3:8b","huggingFaceRepo":"Qwen/Qwen3-8B","sources":{"releaseDate":"https://github.com/QwenLM/Qwen3/blob/main/README.md","license":"https://huggingface.co/Qwen/Qwen3-8B/blob/main/LICENSE","totalParamsB":"https://huggingface.co/Qwen/Qwen3-8B","activeParamsB":"https://huggingface.co/Qwen/Qwen3-8B","numLayers":"https://huggingface.co/Qwen/Qwen3-8B/resolve/main/config.json","numKvHeads":"https://huggingface.co/Qwen/Qwen3-8B/resolve/main/config.json","headDim":"https://huggingface.co/Qwen/Qwen3-8B/resolve/main/config.json","hiddenSize":"https://huggingface.co/Qwen/Qwen3-8B/resolve/main/config.json","maxContextTokens":"https://huggingface.co/Qwen/Qwen3-8B","modalities":"https://huggingface.co/Qwen/Qwen3-8B","huggingFaceRepo":"https://huggingface.co/Qwen/Qwen3-8B","attention":"https://huggingface.co/Qwen/Qwen3-8B/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/Qwen/Qwen3-8B?expand[]=safetensors","ollamaTag":"https://ollama.com/library/qwen3/tags"},"url":{"en":"https://onpremworld.com/en/models/qwen3-8b","zh-tw":"https://onpremworld.com/zh-tw/models/qwen3-8b"}},{"id":"qwen3-32b","name":"Qwen3-32B","family":"Qwen3","developer":"Alibaba Qwen","releaseDate":"2025-04","license":{"name":"Apache-2.0","commercial":true},"architecture":"dense","totalParamsB":32.8,"activeParamsB":32.8,"maxContextTokens":32768,"ollamaTag":"qwen3:32b","huggingFaceRepo":"Qwen/Qwen3-32B","sources":{"releaseDate":"https://github.com/QwenLM/Qwen3/blob/main/README.md","license":"https://huggingface.co/Qwen/Qwen3-32B/blob/main/LICENSE","totalParamsB":"https://huggingface.co/Qwen/Qwen3-32B","activeParamsB":"https://huggingface.co/Qwen/Qwen3-32B","numLayers":"https://huggingface.co/Qwen/Qwen3-32B/resolve/main/config.json","numKvHeads":"https://huggingface.co/Qwen/Qwen3-32B/resolve/main/config.json","headDim":"https://huggingface.co/Qwen/Qwen3-32B/resolve/main/config.json","hiddenSize":"https://huggingface.co/Qwen/Qwen3-32B/resolve/main/config.json","maxContextTokens":"https://huggingface.co/Qwen/Qwen3-32B","modalities":"https://huggingface.co/Qwen/Qwen3-32B","huggingFaceRepo":"https://huggingface.co/Qwen/Qwen3-32B","attention":"https://huggingface.co/Qwen/Qwen3-32B/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/Qwen/Qwen3-32B?expand[]=safetensors","ollamaTag":"https://ollama.com/library/qwen3/tags"},"url":{"en":"https://onpremworld.com/en/models/qwen3-32b","zh-tw":"https://onpremworld.com/zh-tw/models/qwen3-32b"}},{"id":"qwen3-30b-a3b","name":"Qwen3-30B-A3B (2507)","family":"Qwen3","developer":"Alibaba Qwen","releaseDate":"2025-07","license":{"name":"Apache-2.0","commercial":true},"architecture":"moe","totalParamsB":30.5,"activeParamsB":3.3,"maxContextTokens":262144,"ollamaTag":"qwen3:30b-instruct","huggingFaceRepo":"Qwen/Qwen3-30B-A3B-Instruct-2507","sources":{"releaseDate":"https://github.com/QwenLM/Qwen3/blob/main/README.md","license":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507/blob/main/LICENSE","totalParamsB":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507","activeParamsB":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507","numLayers":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507/resolve/main/config.json","numKvHeads":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507/resolve/main/config.json","headDim":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507/resolve/main/config.json","hiddenSize":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507/resolve/main/config.json","maxContextTokens":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507","modalities":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507","huggingFaceRepo":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507","attention":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/Qwen/Qwen3-30B-A3B-Instruct-2507?expand[]=safetensors","ollamaTag":"https://ollama.com/library/qwen3/tags"},"url":{"en":"https://onpremworld.com/en/models/qwen3-30b-a3b","zh-tw":"https://onpremworld.com/zh-tw/models/qwen3-30b-a3b"}},{"id":"qwen3-coder-30b-a3b","name":"Qwen3-Coder-30B-A3B-Instruct","family":"Qwen3-Coder","developer":"Alibaba Qwen","releaseDate":"2025-07","license":{"name":"Apache-2.0","commercial":true},"architecture":"moe","totalParamsB":30.5,"activeParamsB":3.3,"maxContextTokens":262144,"ollamaTag":"qwen3-coder:30b","huggingFaceRepo":"Qwen/Qwen3-Coder-30B-A3B-Instruct","sources":{"releaseDate":"https://simonwillison.net/2025/Jul/31/qwen3-coder-flash/","license":"https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct/blob/main/LICENSE","totalParamsB":"https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct","activeParamsB":"https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct","numLayers":"https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct/resolve/main/config.json","numKvHeads":"https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct/resolve/main/config.json","headDim":"https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct/resolve/main/config.json","hiddenSize":"https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct/resolve/main/config.json","maxContextTokens":"https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct","modalities":"https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct","huggingFaceRepo":"https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct","attention":"https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/Qwen/Qwen3-Coder-30B-A3B-Instruct?expand[]=safetensors","ollamaTag":"https://ollama.com/library/qwen3-coder/tags"},"url":{"en":"https://onpremworld.com/en/models/qwen3-coder-30b-a3b","zh-tw":"https://onpremworld.com/zh-tw/models/qwen3-coder-30b-a3b"}},{"id":"qwen3-coder-next","name":"Qwen3-Coder-Next (80B-A3B)","family":"Qwen3-Coder","developer":"Alibaba Qwen","releaseDate":"2026-02","license":{"name":"Apache-2.0","commercial":true},"architecture":"moe","totalParamsB":80,"activeParamsB":3,"maxContextTokens":262144,"ollamaTag":"qwen3-coder-next:q4_K_M","huggingFaceRepo":"Qwen/Qwen3-Coder-Next","sources":{"releaseDate":"https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.md","license":"https://huggingface.co/Qwen/Qwen3-Coder-Next/blob/main/LICENSE","totalParamsB":"https://huggingface.co/Qwen/Qwen3-Coder-Next","activeParamsB":"https://huggingface.co/Qwen/Qwen3-Coder-Next","numLayers":"https://huggingface.co/Qwen/Qwen3-Coder-Next/resolve/main/config.json","numKvHeads":"https://huggingface.co/Qwen/Qwen3-Coder-Next/resolve/main/config.json","headDim":"https://huggingface.co/Qwen/Qwen3-Coder-Next/resolve/main/config.json","hiddenSize":"https://huggingface.co/Qwen/Qwen3-Coder-Next/resolve/main/config.json","maxContextTokens":"https://huggingface.co/Qwen/Qwen3-Coder-Next","modalities":"https://huggingface.co/Qwen/Qwen3-Coder-Next","huggingFaceRepo":"https://huggingface.co/Qwen/Qwen3-Coder-Next","attention":"https://huggingface.co/Qwen/Qwen3-Coder-Next/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/Qwen/Qwen3-Coder-Next?expand[]=safetensors","ollamaTag":"https://ollama.com/library/qwen3-coder-next/tags"},"url":{"en":"https://onpremworld.com/en/models/qwen3-coder-next","zh-tw":"https://onpremworld.com/zh-tw/models/qwen3-coder-next"}},{"id":"qwen3.5-9b","name":"Qwen3.5-9B","family":"Qwen3.5","developer":"Alibaba Qwen","releaseDate":"2026-03","license":{"name":"Apache-2.0","commercial":true},"architecture":"dense","totalParamsB":9,"activeParamsB":9,"maxContextTokens":262144,"ollamaTag":"qwen3.5:9b","huggingFaceRepo":"Qwen/Qwen3.5-9B","sources":{"releaseDate":"https://github.com/QwenLM/Qwen3.8/blob/main/README.md","license":"https://huggingface.co/Qwen/Qwen3.5-9B/blob/main/LICENSE","totalParamsB":"https://huggingface.co/Qwen/Qwen3.5-9B","activeParamsB":"https://huggingface.co/Qwen/Qwen3.5-9B","numLayers":"https://huggingface.co/Qwen/Qwen3.5-9B/resolve/main/config.json","numKvHeads":"https://huggingface.co/Qwen/Qwen3.5-9B/resolve/main/config.json","headDim":"https://huggingface.co/Qwen/Qwen3.5-9B/resolve/main/config.json","hiddenSize":"https://huggingface.co/Qwen/Qwen3.5-9B/resolve/main/config.json","maxContextTokens":"https://huggingface.co/Qwen/Qwen3.5-9B","modalities":"https://huggingface.co/Qwen/Qwen3.5-9B","huggingFaceRepo":"https://huggingface.co/Qwen/Qwen3.5-9B","attention":"https://huggingface.co/Qwen/Qwen3.5-9B/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/Qwen/Qwen3.5-9B?expand[]=safetensors","ollamaTag":"https://ollama.com/library/qwen3.5/tags"},"url":{"en":"https://onpremworld.com/en/models/qwen3.5-9b","zh-tw":"https://onpremworld.com/zh-tw/models/qwen3.5-9b"}},{"id":"qwen3.5-27b","name":"Qwen3.5-27B","family":"Qwen3.5","developer":"Alibaba Qwen","releaseDate":"2026-02","license":{"name":"Apache-2.0","commercial":true},"architecture":"dense","totalParamsB":27,"activeParamsB":27,"maxContextTokens":262144,"ollamaTag":"qwen3.5:27b","huggingFaceRepo":"Qwen/Qwen3.5-27B","sources":{"releaseDate":"https://github.com/QwenLM/Qwen3.8/blob/main/README.md","license":"https://huggingface.co/Qwen/Qwen3.5-27B/blob/main/LICENSE","totalParamsB":"https://huggingface.co/Qwen/Qwen3.5-27B","activeParamsB":"https://huggingface.co/Qwen/Qwen3.5-27B","numLayers":"https://huggingface.co/Qwen/Qwen3.5-27B/resolve/main/config.json","numKvHeads":"https://huggingface.co/Qwen/Qwen3.5-27B/resolve/main/config.json","headDim":"https://huggingface.co/Qwen/Qwen3.5-27B/resolve/main/config.json","hiddenSize":"https://huggingface.co/Qwen/Qwen3.5-27B/resolve/main/config.json","maxContextTokens":"https://huggingface.co/Qwen/Qwen3.5-27B","modalities":"https://huggingface.co/Qwen/Qwen3.5-27B","huggingFaceRepo":"https://huggingface.co/Qwen/Qwen3.5-27B","attention":"https://huggingface.co/Qwen/Qwen3.5-27B/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/Qwen/Qwen3.5-27B?expand[]=safetensors","ollamaTag":"https://ollama.com/library/qwen3.5/tags"},"url":{"en":"https://onpremworld.com/en/models/qwen3.5-27b","zh-tw":"https://onpremworld.com/zh-tw/models/qwen3.5-27b"}},{"id":"qwen3.5-35b-a3b","name":"Qwen3.5-35B-A3B","family":"Qwen3.5","developer":"Alibaba Qwen","releaseDate":"2026-02","license":{"name":"Apache-2.0","commercial":true},"architecture":"moe","totalParamsB":35,"activeParamsB":3,"maxContextTokens":262144,"ollamaTag":"qwen3.5:35b","huggingFaceRepo":"Qwen/Qwen3.5-35B-A3B","sources":{"releaseDate":"https://github.com/QwenLM/Qwen3.8/blob/main/README.md","license":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B/blob/main/LICENSE","totalParamsB":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B","activeParamsB":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B","numLayers":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B/resolve/main/config.json","numKvHeads":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B/resolve/main/config.json","headDim":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B/resolve/main/config.json","hiddenSize":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B/resolve/main/config.json","maxContextTokens":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B","modalities":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B","huggingFaceRepo":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B","attention":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/Qwen/Qwen3.5-35B-A3B?expand[]=safetensors","ollamaTag":"https://ollama.com/library/qwen3.5/tags"},"url":{"en":"https://onpremworld.com/en/models/qwen3.5-35b-a3b","zh-tw":"https://onpremworld.com/zh-tw/models/qwen3.5-35b-a3b"}},{"id":"qwen3.5-122b-a10b","name":"Qwen3.5-122B-A10B","family":"Qwen3.5","developer":"Alibaba Qwen","releaseDate":"2026-02","license":{"name":"Apache-2.0","commercial":true},"architecture":"moe","totalParamsB":122,"activeParamsB":10,"maxContextTokens":262144,"ollamaTag":"qwen3.5:122b","huggingFaceRepo":"Qwen/Qwen3.5-122B-A10B","sources":{"releaseDate":"https://github.com/QwenLM/Qwen3.8/blob/main/README.md","license":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B/blob/main/LICENSE","totalParamsB":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B","activeParamsB":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B","numLayers":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B/resolve/main/config.json","numKvHeads":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B/resolve/main/config.json","headDim":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B/resolve/main/config.json","hiddenSize":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B/resolve/main/config.json","maxContextTokens":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B","modalities":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B","huggingFaceRepo":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B","attention":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/Qwen/Qwen3.5-122B-A10B?expand[]=safetensors","ollamaTag":"https://ollama.com/library/qwen3.5/tags"},"url":{"en":"https://onpremworld.com/en/models/qwen3.5-122b-a10b","zh-tw":"https://onpremworld.com/zh-tw/models/qwen3.5-122b-a10b"}},{"id":"qwen3.6-27b","name":"Qwen3.6-27B","family":"Qwen3.6","developer":"Alibaba Qwen","releaseDate":"2026-04","license":{"name":"Apache-2.0","commercial":true},"architecture":"dense","totalParamsB":27,"activeParamsB":27,"maxContextTokens":262144,"ollamaTag":"qwen3.6:27b","huggingFaceRepo":"Qwen/Qwen3.6-27B","sources":{"releaseDate":"https://github.com/QwenLM/Qwen3.8/blob/main/README.md","license":"https://huggingface.co/Qwen/Qwen3.6-27B/blob/main/LICENSE","totalParamsB":"https://huggingface.co/Qwen/Qwen3.6-27B","activeParamsB":"https://huggingface.co/Qwen/Qwen3.6-27B","numLayers":"https://huggingface.co/Qwen/Qwen3.6-27B/resolve/main/config.json","numKvHeads":"https://huggingface.co/Qwen/Qwen3.6-27B/resolve/main/config.json","headDim":"https://huggingface.co/Qwen/Qwen3.6-27B/resolve/main/config.json","hiddenSize":"https://huggingface.co/Qwen/Qwen3.6-27B/resolve/main/config.json","maxContextTokens":"https://huggingface.co/Qwen/Qwen3.6-27B","modalities":"https://huggingface.co/Qwen/Qwen3.6-27B","huggingFaceRepo":"https://huggingface.co/Qwen/Qwen3.6-27B","attention":"https://huggingface.co/Qwen/Qwen3.6-27B/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/Qwen/Qwen3.6-27B?expand[]=safetensors","ollamaTag":"https://ollama.com/library/qwen3.6/tags"},"url":{"en":"https://onpremworld.com/en/models/qwen3.6-27b","zh-tw":"https://onpremworld.com/zh-tw/models/qwen3.6-27b"}},{"id":"qwen3.6-35b-a3b","name":"Qwen3.6-35B-A3B","family":"Qwen3.6","developer":"Alibaba Qwen","releaseDate":"2026-04","license":{"name":"Apache-2.0","commercial":true},"architecture":"moe","totalParamsB":35,"activeParamsB":3,"maxContextTokens":262144,"ollamaTag":"qwen3.6:35b","huggingFaceRepo":"Qwen/Qwen3.6-35B-A3B","sources":{"releaseDate":"https://github.com/QwenLM/Qwen3.8/blob/main/README.md","license":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B/blob/main/LICENSE","totalParamsB":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B","activeParamsB":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B","numLayers":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B/resolve/main/config.json","numKvHeads":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B/resolve/main/config.json","headDim":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B/resolve/main/config.json","hiddenSize":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B/resolve/main/config.json","maxContextTokens":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B","modalities":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B","huggingFaceRepo":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B","attention":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/Qwen/Qwen3.6-35B-A3B?expand[]=safetensors","ollamaTag":"https://ollama.com/library/qwen3.6/tags"},"url":{"en":"https://onpremworld.com/en/models/qwen3.6-35b-a3b","zh-tw":"https://onpremworld.com/zh-tw/models/qwen3.6-35b-a3b"}},{"id":"qwen3.8-27b","name":"Qwen3.8-27B","family":"Qwen3.8","developer":"Alibaba Qwen","releaseDate":"2026-08","license":{"name":"Apache-2.0","commercial":true},"architecture":"dense","totalParamsB":27,"activeParamsB":27,"maxContextTokens":262144,"ollamaTag":"qwen3.8:27b","huggingFaceRepo":"Qwen/Qwen3.8-27B","sources":{"releaseDate":"https://github.com/QwenLM/Qwen3.8/blob/main/README.md","license":"https://huggingface.co/Qwen/Qwen3.8-27B/blob/main/LICENSE","totalParamsB":"https://huggingface.co/Qwen/Qwen3.8-27B","activeParamsB":"https://huggingface.co/Qwen/Qwen3.8-27B","numLayers":"https://huggingface.co/Qwen/Qwen3.8-27B/resolve/main/config.json","numKvHeads":"https://huggingface.co/Qwen/Qwen3.8-27B/resolve/main/config.json","headDim":"https://huggingface.co/Qwen/Qwen3.8-27B/resolve/main/config.json","hiddenSize":"https://huggingface.co/Qwen/Qwen3.8-27B/resolve/main/config.json","maxContextTokens":"https://huggingface.co/Qwen/Qwen3.8-27B","modalities":"https://huggingface.co/Qwen/Qwen3.8-27B","huggingFaceRepo":"https://huggingface.co/Qwen/Qwen3.8-27B","attention":"https://huggingface.co/Qwen/Qwen3.8-27B/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/Qwen/Qwen3.8-27B?expand[]=safetensors","ollamaTag":"https://ollama.com/library/qwen3.8/tags"},"url":{"en":"https://onpremworld.com/en/models/qwen3.8-27b","zh-tw":"https://onpremworld.com/zh-tw/models/qwen3.8-27b"}},{"id":"qwen3.8-flash-next","name":"Qwen3.8-Flash-Next","family":"Qwen3.8","developer":"Alibaba Qwen","releaseDate":"2026-08","license":{"name":"Qwen Community License 1.0 (qwen-community-1.0)","commercial":true},"architecture":"moe","totalParamsB":180,"activeParamsB":6,"maxContextTokens":262144,"ollamaTag":"qwen3.8-flash-next:125b-a6b-q4_K_M","huggingFaceRepo":"Qwen/Qwen3.8-Flash-Next","sources":{"releaseDate":"https://github.com/QwenLM/Qwen3.8-Flash-Next/blob/main/README.md","license":"https://huggingface.co/Qwen/Qwen3.8-Flash-Next/blob/main/LICENSE","totalParamsB":"https://huggingface.co/Qwen/Qwen3.8-Flash-Next","activeParamsB":"https://huggingface.co/Qwen/Qwen3.8-Flash-Next","numLayers":"https://huggingface.co/Qwen/Qwen3.8-Flash-Next/resolve/main/config.json","numKvHeads":"https://huggingface.co/Qwen/Qwen3.8-Flash-Next/resolve/main/config.json","headDim":"https://huggingface.co/Qwen/Qwen3.8-Flash-Next/resolve/main/config.json","hiddenSize":"https://huggingface.co/Qwen/Qwen3.8-Flash-Next/resolve/main/config.json","maxContextTokens":"https://huggingface.co/Qwen/Qwen3.8-Flash-Next","modalities":"https://huggingface.co/Qwen/Qwen3.8-Flash-Next","huggingFaceRepo":"https://huggingface.co/Qwen/Qwen3.8-Flash-Next","attention":"https://huggingface.co/Qwen/Qwen3.8-Flash-Next/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/Qwen/Qwen3.8-Flash-Next?expand[]=safetensors","ollamaTag":"https://ollama.com/library/qwen3.8-flash-next/tags"},"url":{"en":"https://onpremworld.com/en/models/qwen3.8-flash-next","zh-tw":"https://onpremworld.com/zh-tw/models/qwen3.8-flash-next"}},{"id":"gemma-3-12b","name":"Gemma 3 12B IT","family":"Gemma 3","developer":"Google DeepMind","releaseDate":"2025-03","license":{"name":"Gemma Terms of Use","commercial":true},"architecture":"dense","totalParamsB":12,"activeParamsB":12,"maxContextTokens":131072,"ollamaTag":"gemma3:12b","huggingFaceRepo":"google/gemma-3-12b-it","sources":{"releaseDate":"https://ai.google.dev/gemma/docs/releases","license":"https://ai.google.dev/gemma/terms","totalParamsB":"https://ai.google.dev/gemma/docs/core/model_card_3","activeParamsB":"https://ai.google.dev/gemma/docs/core/model_card_3","numLayers":"https://huggingface.co/RedHatAI/gemma-3-12b-it/resolve/main/config.json","numKvHeads":"https://huggingface.co/RedHatAI/gemma-3-12b-it/resolve/main/config.json","headDim":"https://github.com/huggingface/transformers/blob/main/src/transformers/models/gemma3/configuration_gemma3.py","hiddenSize":"https://huggingface.co/RedHatAI/gemma-3-12b-it/resolve/main/config.json","maxContextTokens":"https://ai.google.dev/gemma/docs/core/model_card_3","modalities":"https://huggingface.co/google/gemma-3-12b-it","huggingFaceRepo":"https://huggingface.co/google/gemma-3-12b-it","attention":"https://huggingface.co/RedHatAI/gemma-3-12b-it/resolve/main/config.json","architectureCrossCheck":"https://ollama.com/library/gemma3:12b/blobs/13576eb6dd8d","checkpointParamsB":"https://huggingface.co/api/models/google/gemma-3-12b-it?expand[]=safetensors","ollamaTag":"https://ollama.com/library/gemma3/tags"},"url":{"en":"https://onpremworld.com/en/models/gemma-3-12b","zh-tw":"https://onpremworld.com/zh-tw/models/gemma-3-12b"}},{"id":"gemma-3-27b","name":"Gemma 3 27B IT","family":"Gemma 3","developer":"Google DeepMind","releaseDate":"2025-03","license":{"name":"Gemma Terms of Use","commercial":true},"architecture":"dense","totalParamsB":27,"activeParamsB":27,"maxContextTokens":131072,"ollamaTag":"gemma3:27b","huggingFaceRepo":"google/gemma-3-27b-it","sources":{"releaseDate":"https://ai.google.dev/gemma/docs/releases","license":"https://ai.google.dev/gemma/terms","totalParamsB":"https://ai.google.dev/gemma/docs/core/model_card_3","activeParamsB":"https://ai.google.dev/gemma/docs/core/model_card_3","numLayers":"https://huggingface.co/unsloth/gemma-3-27b-it/resolve/main/config.json","numKvHeads":"https://huggingface.co/unsloth/gemma-3-27b-it/resolve/main/config.json","headDim":"https://huggingface.co/unsloth/gemma-3-27b-it/resolve/main/config.json","hiddenSize":"https://huggingface.co/unsloth/gemma-3-27b-it/resolve/main/config.json","maxContextTokens":"https://ai.google.dev/gemma/docs/core/model_card_3","modalities":"https://huggingface.co/google/gemma-3-27b-it","huggingFaceRepo":"https://huggingface.co/google/gemma-3-27b-it","attention":"https://huggingface.co/unsloth/gemma-3-27b-it/resolve/main/config.json","architectureCrossCheck":"https://ollama.com/library/gemma3:27b/blobs/3eb75691d2db","checkpointParamsB":"https://huggingface.co/api/models/google/gemma-3-27b-it?expand[]=safetensors","ollamaTag":"https://ollama.com/library/gemma3/tags"},"url":{"en":"https://onpremworld.com/en/models/gemma-3-27b","zh-tw":"https://onpremworld.com/zh-tw/models/gemma-3-27b"}},{"id":"gemma-4-e4b","name":"Gemma 4 E4B IT","family":"Gemma 4","developer":"Google DeepMind","releaseDate":"2026-03","license":{"name":"Apache-2.0","commercial":true},"architecture":"dense","totalParamsB":8,"activeParamsB":8,"maxContextTokens":131072,"ollamaTag":"gemma4:e4b","huggingFaceRepo":"google/gemma-4-E4B-it","sources":{"releaseDate":"https://ai.google.dev/gemma/docs/releases","license":"https://ai.google.dev/gemma/docs/gemma_4_license","totalParamsB":"https://huggingface.co/google/gemma-4-E4B-it","activeParamsB":"https://huggingface.co/google/gemma-4-E4B-it","numLayers":"https://huggingface.co/google/gemma-4-E4B-it/resolve/main/config.json","numKvHeads":"https://huggingface.co/google/gemma-4-E4B-it/resolve/main/config.json","headDim":"https://huggingface.co/google/gemma-4-E4B-it/resolve/main/config.json","hiddenSize":"https://huggingface.co/google/gemma-4-E4B-it/resolve/main/config.json","maxContextTokens":"https://huggingface.co/google/gemma-4-E4B-it","modalities":"https://huggingface.co/google/gemma-4-E4B-it","huggingFaceRepo":"https://huggingface.co/google/gemma-4-E4B-it","attention":"https://huggingface.co/google/gemma-4-E4B-it/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/google/gemma-4-E4B-it?expand[]=safetensors","ollamaTag":"https://ollama.com/library/gemma4/tags"},"url":{"en":"https://onpremworld.com/en/models/gemma-4-e4b","zh-tw":"https://onpremworld.com/zh-tw/models/gemma-4-e4b"}},{"id":"gemma-4-12b","name":"Gemma 4 12B Unified IT","family":"Gemma 4","developer":"Google DeepMind","releaseDate":"2026-06","license":{"name":"Apache-2.0","commercial":true},"architecture":"dense","totalParamsB":11.95,"activeParamsB":11.95,"maxContextTokens":262144,"ollamaTag":"gemma4:12b","huggingFaceRepo":"google/gemma-4-12B-it","sources":{"releaseDate":"https://ai.google.dev/gemma/docs/releases","license":"https://ai.google.dev/gemma/docs/gemma_4_license","totalParamsB":"https://huggingface.co/google/gemma-4-12B-it","activeParamsB":"https://huggingface.co/google/gemma-4-12B-it","numLayers":"https://huggingface.co/google/gemma-4-12B-it/resolve/main/config.json","numKvHeads":"https://huggingface.co/google/gemma-4-12B-it/resolve/main/config.json","headDim":"https://huggingface.co/google/gemma-4-12B-it/resolve/main/config.json","hiddenSize":"https://huggingface.co/google/gemma-4-12B-it/resolve/main/config.json","maxContextTokens":"https://huggingface.co/google/gemma-4-12B-it","modalities":"https://huggingface.co/google/gemma-4-12B-it","huggingFaceRepo":"https://huggingface.co/google/gemma-4-12B-it","attention":"https://huggingface.co/google/gemma-4-12B-it/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/google/gemma-4-12B-it?expand[]=safetensors","ollamaTag":"https://ollama.com/library/gemma4/tags"},"url":{"en":"https://onpremworld.com/en/models/gemma-4-12b","zh-tw":"https://onpremworld.com/zh-tw/models/gemma-4-12b"}},{"id":"gemma-4-26b-a4b","name":"Gemma 4 26B A4B IT","family":"Gemma 4","developer":"Google DeepMind","releaseDate":"2026-03","license":{"name":"Apache-2.0","commercial":true},"architecture":"moe","totalParamsB":25.2,"activeParamsB":3.8,"maxContextTokens":262144,"ollamaTag":"gemma4:26b","huggingFaceRepo":"google/gemma-4-26B-A4B-it","sources":{"releaseDate":"https://ai.google.dev/gemma/docs/releases","license":"https://ai.google.dev/gemma/docs/gemma_4_license","totalParamsB":"https://huggingface.co/google/gemma-4-26B-A4B-it","activeParamsB":"https://huggingface.co/google/gemma-4-26B-A4B-it","numLayers":"https://huggingface.co/google/gemma-4-26B-A4B-it/resolve/main/config.json","numKvHeads":"https://huggingface.co/google/gemma-4-26B-A4B-it/resolve/main/config.json","headDim":"https://huggingface.co/google/gemma-4-26B-A4B-it/resolve/main/config.json","hiddenSize":"https://huggingface.co/google/gemma-4-26B-A4B-it/resolve/main/config.json","maxContextTokens":"https://huggingface.co/google/gemma-4-26B-A4B-it","modalities":"https://huggingface.co/google/gemma-4-26B-A4B-it","huggingFaceRepo":"https://huggingface.co/google/gemma-4-26B-A4B-it","attention":"https://huggingface.co/google/gemma-4-26B-A4B-it/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/google/gemma-4-26B-A4B-it?expand[]=safetensors","ollamaTag":"https://ollama.com/library/gemma4/tags"},"url":{"en":"https://onpremworld.com/en/models/gemma-4-26b-a4b","zh-tw":"https://onpremworld.com/zh-tw/models/gemma-4-26b-a4b"}},{"id":"gemma-4-31b","name":"Gemma 4 31B IT","family":"Gemma 4","developer":"Google DeepMind","releaseDate":"2026-03","license":{"name":"Apache-2.0","commercial":true},"architecture":"dense","totalParamsB":30.7,"activeParamsB":30.7,"maxContextTokens":262144,"ollamaTag":"gemma4:31b","huggingFaceRepo":"google/gemma-4-31B-it","sources":{"releaseDate":"https://ai.google.dev/gemma/docs/releases","license":"https://ai.google.dev/gemma/docs/gemma_4_license","totalParamsB":"https://huggingface.co/google/gemma-4-31B-it","activeParamsB":"https://huggingface.co/google/gemma-4-31B-it","numLayers":"https://huggingface.co/google/gemma-4-31B-it/resolve/main/config.json","numKvHeads":"https://huggingface.co/google/gemma-4-31B-it/resolve/main/config.json","headDim":"https://huggingface.co/google/gemma-4-31B-it/resolve/main/config.json","hiddenSize":"https://huggingface.co/google/gemma-4-31B-it/resolve/main/config.json","maxContextTokens":"https://huggingface.co/google/gemma-4-31B-it","modalities":"https://huggingface.co/google/gemma-4-31B-it","huggingFaceRepo":"https://huggingface.co/google/gemma-4-31B-it","attention":"https://huggingface.co/google/gemma-4-31B-it/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/google/gemma-4-31B-it?expand[]=safetensors","ollamaTag":"https://ollama.com/library/gemma4/tags"},"url":{"en":"https://onpremworld.com/en/models/gemma-4-31b","zh-tw":"https://onpremworld.com/zh-tw/models/gemma-4-31b"}},{"id":"mistral-small-3.2-24b","name":"Mistral Small 3.2 24B Instruct (2506)","family":"Mistral Small 3","developer":"Mistral AI","releaseDate":"2025-06","license":{"name":"Apache-2.0","commercial":true},"architecture":"dense","totalParamsB":24,"activeParamsB":24,"maxContextTokens":131072,"ollamaTag":"mistral-small3.2:24b","huggingFaceRepo":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","sources":{"releaseDate":"https://docs.mistral.ai/getting-started/changelog/","license":"https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506","totalParamsB":"https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506","activeParamsB":"https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506","numLayers":"https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506/resolve/main/config.json","numKvHeads":"https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506/resolve/main/config.json","headDim":"https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506/resolve/main/config.json","hiddenSize":"https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506/resolve/main/config.json","maxContextTokens":"https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506/resolve/main/config.json","modalities":"https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506","huggingFaceRepo":"https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506","attention":"https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/mistralai/Mistral-Small-3.2-24B-Instruct-2506?expand[]=safetensors","ollamaTag":"https://ollama.com/library/mistral-small3.2/tags"},"url":{"en":"https://onpremworld.com/en/models/mistral-small-3.2-24b","zh-tw":"https://onpremworld.com/zh-tw/models/mistral-small-3.2-24b"}},{"id":"magistral-small-2509","name":"Magistral Small 1.2 (2509)","family":"Magistral","developer":"Mistral AI","releaseDate":"2025-09","license":{"name":"Apache-2.0","commercial":true},"architecture":"dense","totalParamsB":24,"activeParamsB":24,"maxContextTokens":131072,"ollamaTag":null,"huggingFaceRepo":"mistralai/Magistral-Small-2509","sources":{"releaseDate":"https://docs.mistral.ai/getting-started/changelog/","license":"https://huggingface.co/mistralai/Magistral-Small-2509","totalParamsB":"https://huggingface.co/mistralai/Magistral-Small-2509","activeParamsB":"https://huggingface.co/mistralai/Magistral-Small-2509","numLayers":"https://huggingface.co/mistralai/Magistral-Small-2509/resolve/main/config.json","numKvHeads":"https://huggingface.co/mistralai/Magistral-Small-2509/resolve/main/config.json","headDim":"https://huggingface.co/mistralai/Magistral-Small-2509/resolve/main/config.json","hiddenSize":"https://huggingface.co/mistralai/Magistral-Small-2509/resolve/main/config.json","maxContextTokens":"https://huggingface.co/mistralai/Magistral-Small-2509","modalities":"https://huggingface.co/mistralai/Magistral-Small-2509","huggingFaceRepo":"https://huggingface.co/mistralai/Magistral-Small-2509","attention":"https://huggingface.co/mistralai/Magistral-Small-2509/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/mistralai/Magistral-Small-2509?expand[]=safetensors"},"url":{"en":"https://onpremworld.com/en/models/magistral-small-2509","zh-tw":"https://onpremworld.com/zh-tw/models/magistral-small-2509"}},{"id":"devstral-small-2-24b","name":"Devstral Small 2 24B Instruct (2512)","family":"Devstral","developer":"Mistral AI","releaseDate":"2025-12","license":{"name":"Apache-2.0","commercial":true},"architecture":"dense","totalParamsB":24,"activeParamsB":24,"maxContextTokens":262144,"ollamaTag":"devstral-small-2:24b","huggingFaceRepo":"mistralai/Devstral-Small-2-24B-Instruct-2512","sources":{"releaseDate":"https://docs.mistral.ai/getting-started/changelog/","license":"https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512","totalParamsB":"https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512","activeParamsB":"https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512","numLayers":"https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512/resolve/main/config.json","numKvHeads":"https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512/resolve/main/config.json","headDim":"https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512/resolve/main/config.json","hiddenSize":"https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512/resolve/main/config.json","maxContextTokens":"https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512","modalities":"https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512","huggingFaceRepo":"https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512","attention":"https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/mistralai/Devstral-Small-2-24B-Instruct-2512?expand[]=safetensors","ollamaTag":"https://ollama.com/library/devstral-small-2/tags"},"url":{"en":"https://onpremworld.com/en/models/devstral-small-2-24b","zh-tw":"https://onpremworld.com/zh-tw/models/devstral-small-2-24b"}},{"id":"mistral-small-4-119b","name":"Mistral Small 4 119B (2603)","family":"Mistral Small 4","developer":"Mistral AI","releaseDate":"2026-03","license":{"name":"Apache-2.0","commercial":true},"architecture":"moe","totalParamsB":119,"activeParamsB":6.5,"maxContextTokens":262144,"ollamaTag":null,"huggingFaceRepo":"mistralai/Mistral-Small-4-119B-2603","sources":{"releaseDate":"https://docs.mistral.ai/getting-started/changelog/","license":"https://huggingface.co/mistralai/Mistral-Small-4-119B-2603","totalParamsB":"https://huggingface.co/mistralai/Mistral-Small-4-119B-2603","activeParamsB":"https://huggingface.co/mistralai/Mistral-Small-4-119B-2603","numLayers":"https://huggingface.co/mistralai/Mistral-Small-4-119B-2603/resolve/main/config.json","numKvHeads":"https://huggingface.co/mistralai/Mistral-Small-4-119B-2603/resolve/main/config.json","headDim":"https://huggingface.co/mistralai/Mistral-Small-4-119B-2603/resolve/main/config.json","hiddenSize":"https://huggingface.co/mistralai/Mistral-Small-4-119B-2603/resolve/main/config.json","maxContextTokens":"https://huggingface.co/mistralai/Mistral-Small-4-119B-2603","modalities":"https://huggingface.co/mistralai/Mistral-Small-4-119B-2603","huggingFaceRepo":"https://huggingface.co/mistralai/Mistral-Small-4-119B-2603","attention":"https://huggingface.co/mistralai/Mistral-Small-4-119B-2603/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/mistralai/Mistral-Small-4-119B-2603?expand[]=safetensors"},"url":{"en":"https://onpremworld.com/en/models/mistral-small-4-119b","zh-tw":"https://onpremworld.com/zh-tw/models/mistral-small-4-119b"}},{"id":"deepseek-r1-0528-qwen3-8b","name":"DeepSeek-R1-0528-Qwen3-8B","family":"DeepSeek-R1","developer":"DeepSeek","releaseDate":"2025-05","license":{"name":"MIT","commercial":true},"architecture":"dense","totalParamsB":8.19,"activeParamsB":8.19,"maxContextTokens":131072,"ollamaTag":"deepseek-r1:8b","huggingFaceRepo":"deepseek-ai/DeepSeek-R1-0528-Qwen3-8B","sources":{"releaseDate":"https://api-docs.deepseek.com/news/news250528","license":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B","totalParamsB":"https://huggingface.co/api/models/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B?expand[]=safetensors","activeParamsB":"https://huggingface.co/api/models/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B?expand[]=safetensors","numLayers":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B/resolve/main/config.json","numKvHeads":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B/resolve/main/config.json","headDim":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B/resolve/main/config.json","hiddenSize":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B/resolve/main/config.json","maxContextTokens":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B/resolve/main/config.json","modalities":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B","huggingFaceRepo":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B","attention":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B?expand[]=safetensors","ollamaTag":"https://ollama.com/library/deepseek-r1/tags"},"url":{"en":"https://onpremworld.com/en/models/deepseek-r1-0528-qwen3-8b","zh-tw":"https://onpremworld.com/zh-tw/models/deepseek-r1-0528-qwen3-8b"}},{"id":"deepseek-r1-distill-qwen-32b","name":"DeepSeek-R1-Distill-Qwen-32B","family":"DeepSeek-R1","developer":"DeepSeek","releaseDate":"2025-01","license":{"name":"MIT","commercial":true},"architecture":"dense","totalParamsB":32.76,"activeParamsB":32.76,"maxContextTokens":131072,"ollamaTag":"deepseek-r1:32b","huggingFaceRepo":"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","sources":{"releaseDate":"https://api-docs.deepseek.com/news/news250120","license":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","totalParamsB":"https://huggingface.co/api/models/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B?expand[]=safetensors","activeParamsB":"https://huggingface.co/api/models/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B?expand[]=safetensors","numLayers":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/resolve/main/config.json","numKvHeads":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/resolve/main/config.json","headDim":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/resolve/main/config.json","hiddenSize":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/resolve/main/config.json","maxContextTokens":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/resolve/main/config.json","modalities":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","huggingFaceRepo":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","attention":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B?expand[]=safetensors","ollamaTag":"https://ollama.com/library/deepseek-r1/tags"},"url":{"en":"https://onpremworld.com/en/models/deepseek-r1-distill-qwen-32b","zh-tw":"https://onpremworld.com/zh-tw/models/deepseek-r1-distill-qwen-32b"}},{"id":"deepseek-r1-0528","name":"DeepSeek-R1-0528 (671B)","family":"DeepSeek-R1","developer":"DeepSeek","releaseDate":"2025-05","license":{"name":"MIT","commercial":true},"architecture":"moe","totalParamsB":671,"activeParamsB":37,"maxContextTokens":131072,"ollamaTag":"deepseek-r1:671b","huggingFaceRepo":"deepseek-ai/DeepSeek-R1-0528","sources":{"releaseDate":"https://api-docs.deepseek.com/news/news250528","license":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528","totalParamsB":"https://huggingface.co/deepseek-ai/DeepSeek-R1","activeParamsB":"https://huggingface.co/deepseek-ai/DeepSeek-R1","numLayers":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528/resolve/main/config.json","numKvHeads":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528/resolve/main/config.json","headDim":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528/resolve/main/config.json","hiddenSize":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528/resolve/main/config.json","maxContextTokens":"https://huggingface.co/deepseek-ai/DeepSeek-R1","modalities":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528","huggingFaceRepo":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528","attention":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/deepseek-ai/DeepSeek-R1-0528?expand[]=safetensors","ollamaTag":"https://ollama.com/library/deepseek-r1/tags"},"url":{"en":"https://onpremworld.com/en/models/deepseek-r1-0528","zh-tw":"https://onpremworld.com/zh-tw/models/deepseek-r1-0528"}},{"id":"deepseek-v4-flash","name":"DeepSeek-V4-Flash","family":"DeepSeek-V4","developer":"DeepSeek","releaseDate":"2026-04","license":{"name":"MIT","commercial":true},"architecture":"moe","totalParamsB":284,"activeParamsB":13,"maxContextTokens":1048576,"ollamaTag":null,"huggingFaceRepo":"deepseek-ai/DeepSeek-V4-Flash","sources":{"releaseDate":"https://api-docs.deepseek.com/news/news260424","license":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash","totalParamsB":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash","activeParamsB":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash","numLayers":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash/resolve/main/config.json","numKvHeads":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash/resolve/main/config.json","headDim":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash/resolve/main/config.json","hiddenSize":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash/resolve/main/config.json","maxContextTokens":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash","modalities":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash","huggingFaceRepo":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash","attention":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash/resolve/main/config.json"},"url":{"en":"https://onpremworld.com/en/models/deepseek-v4-flash","zh-tw":"https://onpremworld.com/zh-tw/models/deepseek-v4-flash"}},{"id":"gpt-oss-20b","name":"gpt-oss-20b","family":"gpt-oss","developer":"OpenAI","releaseDate":"2025-08","license":{"name":"Apache-2.0","commercial":true},"architecture":"moe","totalParamsB":21,"activeParamsB":3.6,"maxContextTokens":131072,"ollamaTag":"gpt-oss:20b","huggingFaceRepo":"openai/gpt-oss-20b","sources":{"releaseDate":"https://openai.com/index/introducing-gpt-oss/","license":"https://huggingface.co/openai/gpt-oss-20b","totalParamsB":"https://huggingface.co/openai/gpt-oss-20b","activeParamsB":"https://huggingface.co/openai/gpt-oss-20b","numLayers":"https://huggingface.co/openai/gpt-oss-20b/resolve/main/config.json","numKvHeads":"https://huggingface.co/openai/gpt-oss-20b/resolve/main/config.json","headDim":"https://huggingface.co/openai/gpt-oss-20b/resolve/main/config.json","hiddenSize":"https://huggingface.co/openai/gpt-oss-20b/resolve/main/config.json","maxContextTokens":"https://huggingface.co/openai/gpt-oss-20b/resolve/main/config.json","modalities":"https://huggingface.co/openai/gpt-oss-20b","huggingFaceRepo":"https://huggingface.co/openai/gpt-oss-20b","attention":"https://huggingface.co/openai/gpt-oss-20b/resolve/main/config.json","ollamaTag":"https://ollama.com/library/gpt-oss/tags"},"url":{"en":"https://onpremworld.com/en/models/gpt-oss-20b","zh-tw":"https://onpremworld.com/zh-tw/models/gpt-oss-20b"}},{"id":"gpt-oss-120b","name":"gpt-oss-120b","family":"gpt-oss","developer":"OpenAI","releaseDate":"2025-08","license":{"name":"Apache-2.0","commercial":true},"architecture":"moe","totalParamsB":117,"activeParamsB":5.1,"maxContextTokens":131072,"ollamaTag":"gpt-oss:120b","huggingFaceRepo":"openai/gpt-oss-120b","sources":{"releaseDate":"https://openai.com/index/introducing-gpt-oss/","license":"https://huggingface.co/openai/gpt-oss-120b","totalParamsB":"https://huggingface.co/openai/gpt-oss-120b","activeParamsB":"https://huggingface.co/openai/gpt-oss-120b","numLayers":"https://huggingface.co/openai/gpt-oss-120b/resolve/main/config.json","numKvHeads":"https://huggingface.co/openai/gpt-oss-120b/resolve/main/config.json","headDim":"https://huggingface.co/openai/gpt-oss-120b/resolve/main/config.json","hiddenSize":"https://huggingface.co/openai/gpt-oss-120b/resolve/main/config.json","maxContextTokens":"https://huggingface.co/openai/gpt-oss-120b/resolve/main/config.json","modalities":"https://huggingface.co/openai/gpt-oss-120b","huggingFaceRepo":"https://huggingface.co/openai/gpt-oss-120b","attention":"https://huggingface.co/openai/gpt-oss-120b/resolve/main/config.json","ollamaTag":"https://ollama.com/library/gpt-oss/tags"},"url":{"en":"https://onpremworld.com/en/models/gpt-oss-120b","zh-tw":"https://onpremworld.com/zh-tw/models/gpt-oss-120b"}},{"id":"phi-4","name":"Phi-4 (14B)","family":"Phi-4","developer":"Microsoft","releaseDate":"2024-12","license":{"name":"MIT","commercial":true},"architecture":"dense","totalParamsB":14,"activeParamsB":14,"maxContextTokens":16384,"ollamaTag":"phi4:14b","huggingFaceRepo":"microsoft/phi-4","sources":{"releaseDate":"https://huggingface.co/microsoft/phi-4","license":"https://huggingface.co/microsoft/phi-4/resolve/main/LICENSE","totalParamsB":"https://huggingface.co/microsoft/phi-4","activeParamsB":"https://huggingface.co/microsoft/phi-4","numLayers":"https://huggingface.co/microsoft/phi-4/resolve/main/config.json","numKvHeads":"https://huggingface.co/microsoft/phi-4/resolve/main/config.json","headDim":"https://huggingface.co/microsoft/phi-4/resolve/main/config.json","hiddenSize":"https://huggingface.co/microsoft/phi-4/resolve/main/config.json","maxContextTokens":"https://huggingface.co/microsoft/phi-4","modalities":"https://huggingface.co/microsoft/phi-4","huggingFaceRepo":"https://huggingface.co/microsoft/phi-4","attention":"https://huggingface.co/microsoft/phi-4/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/microsoft/phi-4?expand[]=safetensors","ollamaTag":"https://ollama.com/library/phi4/tags"},"url":{"en":"https://onpremworld.com/en/models/phi-4","zh-tw":"https://onpremworld.com/zh-tw/models/phi-4"}},{"id":"glm-4.5-air","name":"GLM-4.5-Air","family":"GLM-4.5","developer":"Zhipu AI (Z.ai)","releaseDate":"2025-07","license":{"name":"MIT","commercial":true},"architecture":"moe","totalParamsB":106,"activeParamsB":12,"maxContextTokens":131072,"ollamaTag":null,"huggingFaceRepo":"zai-org/GLM-4.5-Air","sources":{"releaseDate":"https://z.ai/blog/glm-4.5","license":"https://huggingface.co/zai-org/GLM-4.5-Air","totalParamsB":"https://huggingface.co/zai-org/GLM-4.5-Air","activeParamsB":"https://huggingface.co/zai-org/GLM-4.5-Air","numLayers":"https://huggingface.co/zai-org/GLM-4.5-Air/resolve/main/config.json","numKvHeads":"https://huggingface.co/zai-org/GLM-4.5-Air/resolve/main/config.json","headDim":"https://huggingface.co/zai-org/GLM-4.5-Air/resolve/main/config.json","hiddenSize":"https://huggingface.co/zai-org/GLM-4.5-Air/resolve/main/config.json","maxContextTokens":"https://huggingface.co/zai-org/GLM-4.5-Air/resolve/main/config.json","modalities":"https://huggingface.co/zai-org/GLM-4.5-Air","huggingFaceRepo":"https://huggingface.co/zai-org/GLM-4.5-Air","attention":"https://huggingface.co/zai-org/GLM-4.5-Air/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/zai-org/GLM-4.5-Air?expand[]=safetensors"},"url":{"en":"https://onpremworld.com/en/models/glm-4.5-air","zh-tw":"https://onpremworld.com/zh-tw/models/glm-4.5-air"}},{"id":"glm-4.7-flash","name":"GLM-4.7-Flash (30B-A3B)","family":"GLM-4.7","developer":"Zhipu AI (Z.ai)","releaseDate":"2026-01","license":{"name":"MIT","commercial":true},"architecture":"moe","totalParamsB":30,"activeParamsB":3,"maxContextTokens":202752,"ollamaTag":"glm-4.7-flash:q4_K_M","huggingFaceRepo":"zai-org/GLM-4.7-Flash","sources":{"releaseDate":"https://gigazine.net/gsc_news/en/20260120-zai-glm-4-7-flash","license":"https://huggingface.co/zai-org/GLM-4.7-Flash","totalParamsB":"https://huggingface.co/zai-org/GLM-4.7-Flash","activeParamsB":"https://huggingface.co/zai-org/GLM-4.7-Flash","numLayers":"https://huggingface.co/zai-org/GLM-4.7-Flash/resolve/main/config.json","numKvHeads":"https://huggingface.co/zai-org/GLM-4.7-Flash/resolve/main/config.json","headDim":"https://huggingface.co/zai-org/GLM-4.7-Flash/resolve/main/config.json","hiddenSize":"https://huggingface.co/zai-org/GLM-4.7-Flash/resolve/main/config.json","maxContextTokens":"https://huggingface.co/zai-org/GLM-4.7-Flash/resolve/main/config.json","modalities":"https://huggingface.co/zai-org/GLM-4.7-Flash","huggingFaceRepo":"https://huggingface.co/zai-org/GLM-4.7-Flash","attention":"https://huggingface.co/zai-org/GLM-4.7-Flash/resolve/main/config.json","checkpointParamsB":"https://huggingface.co/api/models/zai-org/GLM-4.7-Flash?expand[]=safetensors","ollamaTag":"https://ollama.com/library/glm-4.7-flash/tags"},"url":{"en":"https://onpremworld.com/en/models/glm-4.7-flash","zh-tw":"https://onpremworld.com/zh-tw/models/glm-4.7-flash"}},{"id":"kimi-k2.6","name":"Kimi K2.6","family":"Kimi K2","developer":"Moonshot AI","releaseDate":"2026-04","license":{"name":"Modified MIT","commercial":true},"architecture":"moe","totalParamsB":1000,"activeParamsB":32,"maxContextTokens":262144,"ollamaTag":null,"huggingFaceRepo":"moonshotai/Kimi-K2.6","sources":{"releaseDate":"https://datanorth.ai/news/moonshot-ai-releases-kimi-k2-6","license":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/main/LICENSE","totalParamsB":"https://huggingface.co/moonshotai/Kimi-K2.6","activeParamsB":"https://huggingface.co/moonshotai/Kimi-K2.6","numLayers":"https://huggingface.co/moonshotai/Kimi-K2.6/resolve/main/config.json","numKvHeads":"https://huggingface.co/moonshotai/Kimi-K2.6/resolve/main/config.json","headDim":"https://huggingface.co/moonshotai/Kimi-K2.6/resolve/main/config.json","hiddenSize":"https://huggingface.co/moonshotai/Kimi-K2.6/resolve/main/config.json","maxContextTokens":"https://huggingface.co/moonshotai/Kimi-K2.6","modalities":"https://huggingface.co/moonshotai/Kimi-K2.6","huggingFaceRepo":"https://huggingface.co/moonshotai/Kimi-K2.6","attention":"https://huggingface.co/moonshotai/Kimi-K2.6/resolve/main/config.json"},"url":{"en":"https://onpremworld.com/en/models/kimi-k2.6","zh-tw":"https://onpremworld.com/zh-tw/models/kimi-k2.6"}}]}