4-bit Open on Hugging Face
Parameters
12B
Weights (est.)
≈ 6.8 GB
Mac memory (est.)
16 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-4-12B-it-qat-OptiQ-4bit --prompt "Hello"
Details
- Base model
- google/gemma-4-12B-it-qat-q4_0-unquantized (quantized)
- Vendor
- Google · Gemma
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 5.5K in the last 30 days · 29K all time · 22 likes
- Published
- 2026-06-15 · updated 2026-10-18 (24d ago)
- Tags
- gemma4_unified, quantized, mixed-precision, 4bit, 8bit, optiq, apple-silicon, image-text-to-text, gemma-4
Other MLX builds of google/gemma-4-12B-it-qat-q4_0-unquantized
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Huihui-gemma-4-12B-it-qat-q4_0-unquantized-abliterated-5bit-msq | 5-bit | ≈ 3.7 GB | 8 GB+ | 179 |
| gemma-4-12B-it-qat-OptiQ-4bit (this one) | 4-bit | ≈ 6.8 GB | 16 GB+ | 5.5K |