gemma-4-31B-it-qat-assistant-4bit
mlx-community/gemma-4-31B-it-qat-assistant-4bit
Text generation · mlx
4-bit Open on Hugging Face
Parameters
470M
Weights (est.)
≈ 264 MB
Mac memory (est.)
8 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/gemma-4-31B-it-qat-assistant-4bit --prompt "Hello"
Details
- Base model
- google/gemma-4-31B-it-qat-q4_0-unquantized-assistant (quantized)
- Vendor
- Google · Gemma
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- gemma
- Downloads
- 243 in the last 30 days · 2.6K all time · 0 likes
- Published
- 2026-06-05 · updated 2026-06-05 (5mo ago)
- Languages
- en
- Tags
- gemma4_assistant, mlx-vlm, gemma-4, gemma-4-31b, gemma, speculative-decoding, draft-model, 4bit
Other MLX builds of google/gemma-4-31B-it-qat-q4_0-unquantized-assistant
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| gemma-4-31B-it-qat-assistant-4bit (this one) | 4-bit | ≈ 264 MB | 8 GB+ | 243 |
| gemma-4-31B-it-qat-assistant-mxfp4 | MXFP4 | ≈ 264 MB | 8 GB+ | 53 |
| gemma-4-31B-it-qat-assistant-nvfp4 | 4-bit | ≈ 264 MB | 8 GB+ | 52 |
| gemma-4-31B-it-qat-assistant-5bit | 5-bit | ≈ 323 MB | 8 GB+ | 52 |
| gemma-4-31B-it-qat-assistant-6bit | 6-bit | ≈ 382 MB | 8 GB+ | 44 |
| gemma-4-31B-it-qat-assistant-8bit | 8-bit | ≈ 499 MB | 8 GB+ | 105 |
| gemma-4-31B-it-qat-assistant-mxfp8 | MXFP8 | ≈ 499 MB | 8 GB+ | 67 |
| gemma-4-31B-it-qat-assistant-bf16 | bf16 | ≈ 939 MB | 8 GB+ | 94 |