Qwen3.5-122B-A10B
Qwen3.5-122B-A10B by Alibaba Qwen (122B parameters, MoE with 10B active per token). At Q4_K_M with an 8K context it needs about 73.0 GiB of memory. A 122B MoE with 10B active: a model for 128 GB unified-memory machines or a 96 GB workstation card.
Last updated: 2026-10-13
Model facts
| Developer | Alibaba Qwen |
|---|---|
| Parameters | 122B (10B active, MoE)[src] |
| Native context | 262,144 tokens[src] |
| Licence | Apache-2.0[src] |
| Commercial use | Yes |
| KV cache | 12 of 48 layers (the rest are linear attention with a fixed-size state)[src] |
| Released | 2026-02 |
Good for: reasoning · coding · agents · Chinese · 128GB unified-memory machines
Run it
ollama run qwen3.5:122b
Memory needed
Weights + KV cache + runtime overhead, in GiB. Lower quantization = less memory, slightly lower quality.
| Quantization | 4K context | 8K context | 32K context |
|---|---|---|---|
| Q4_K_M | 72.9 GiB | 73.0 GiB | 73.6 GiB |
| Q5_K_M | 85.4 GiB | 85.5 GiB | 86.1 GiB |
| Q6_K | 98.9 GiB | 99.0 GiB | 99.5 GiB |
| Q8_0 | 127.4 GiB | 127.4 GiB | 128.0 GiB |
| FP16 | 239.2 GiB | 239.3 GiB | 239.9 GiB |
Which hardware runs it
Best quantization that fits each device with a 8K context. Estimates, not benchmarks. See the methodology.
Frequently asked questions
How much VRAM does Qwen3.5-122B-A10B need?
With an 8K context, about 73.0 GiB at Q4_K_M and 127.4 GiB at Q8_0 (weights + KV cache + runtime overhead). Longer contexts need more memory for the KV cache.
Can Qwen3.5-122B-A10B run on an GeForce RTX 4090?
Qwen3.5-122B-A10B does not fit on the GeForce RTX 4090 (24 GB), even at Q4_K_M with an 8K context.
Can I run Qwen3.5-122B-A10B on a Mac?
Yes. Qwen3.5-122B-A10B fits on the M3 Ultra (256 GB) at Q8_0 with an 8K context, using about 127.4 GiB, at an estimated 50 tokens/s.
Can Qwen3.5-122B-A10B be used commercially?
Qwen3.5-122B-A10B is released under Apache-2.0. The licence allows commercial use (read its conditions).
Sources
- https://github.com/QwenLM/Qwen3.8/blob/main/README.md
- https://huggingface.co/Qwen/Qwen3.5-122B-A10B/blob/main/LICENSE
- https://huggingface.co/Qwen/Qwen3.5-122B-A10B
- https://huggingface.co/Qwen/Qwen3.5-122B-A10B/resolve/main/config.json
- https://huggingface.co/api/models/Qwen/Qwen3.5-122B-A10B?expand[]=safetensors
- https://ollama.com/library/qwen3.5/tags