Gemma 3 12B IT
Gemma 3 12B IT by Google DeepMind (12B parameters). At Q4_K_M with an 8K context it needs about 8.4 GiB of memory. Google's 12B with image input and support for 140+ languages; it fits a 12 GB card at 6-bit.
Last updated: 2026-10-13
Model facts
Run it
ollama run gemma3:12b
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 | 8.2 GiB | 8.4 GiB | 9.9 GiB |
| Q5_K_M | 9.4 GiB | 9.7 GiB | 11.2 GiB |
| Q6_K | 10.7 GiB | 11.0 GiB | 12.5 GiB |
| Q8_0 | 13.5 GiB | 13.8 GiB | 15.3 GiB |
| FP16 | 24.5 GiB | 24.8 GiB | 26.3 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 Gemma 3 12B IT need?
With an 8K context, about 8.4 GiB at Q4_K_M and 13.8 GiB at Q8_0 (weights + KV cache + runtime overhead). Longer contexts need more memory for the KV cache.
Can Gemma 3 12B IT run on an GeForce RTX 4090?
Yes. Gemma 3 12B IT fits on the GeForce RTX 4090 (24 GB) at Q8_0 with an 8K context, using about 13.8 GiB, at an estimated 55 tokens/s.
Can I run Gemma 3 12B IT on a Mac?
Yes. Gemma 3 12B IT fits on the M3 Ultra (96 GB) at FP16 with an 8K context, using about 24.8 GiB, at an estimated 22 tokens/s.
Can Gemma 3 12B IT be used commercially?
Gemma 3 12B IT is released under Gemma Terms of Use. The licence allows commercial use (read its conditions).
Sources
- https://ai.google.dev/gemma/docs/releases
- https://ai.google.dev/gemma/terms
- https://ai.google.dev/gemma/docs/core/model_card_3
- https://huggingface.co/RedHatAI/gemma-3-12b-it/resolve/main/config.json
- https://github.com/huggingface/transformers/blob/main/src/transformers/models/gemma3/configuration_gemma3.py
- https://huggingface.co/google/gemma-3-12b-it
- https://ollama.com/library/gemma3:12b/blobs/13576eb6dd8d
- https://huggingface.co/api/models/google/gemma-3-12b-it?expand[]=safetensors
- https://ollama.com/library/gemma3/tags