4-bit Open on Hugging Face
Parameters
12B
Weights (est.)
≈ 6.6 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-3-12b-pt-4bit-text --prompt "Hello"
Details
- Base model
- google/gemma-3-12b-pt (quantized)
- Vendor
- Google · Gemma
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- gemma
- Downloads
- 54 in the last 30 days · 841 all time · 0 likes
- Published
- 2026-02-23 · updated 2026-02-23 (8mo ago)
- Tags
- gemma3
Other MLX builds of google/gemma-3-12b-pt
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| gemma-3-12b-pt-4bit-text (this one) | 4-bit | ≈ 6.6 GB | 16 GB+ | 54 |
| gemma-3-12b-it-bf16 | bf16 | ≈ 26.4 GB | 32 GB+ | 1.7K |
| gemma-3-12b-it-4bit | 4-bit | — | — | 15K |
| gemma-3-12b-it-8bit | 8-bit | — | — | 336 |
| gemma-3-12b-it-6bit | 6-bit | — | — | 78 |