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/translategemma-12b-it-4bit --prompt "Hello"
Details
- Base model
- google/translategemma-12b-it (quantized)
- Vendor
- Google · Gemma
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- gemma
- Downloads
- 1.5K in the last 30 days · 9.2K all time · 6 likes
- Published
- 2026-01-15 · updated 2026-01-16 (9mo ago)
- Tags
- gemma3
Other MLX builds of google/translategemma-12b-it
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| translategemma-12b-it-4bit (this one) | 4-bit | ≈ 6.6 GB | 16 GB+ | 1.5K |
| translategemma-12b-it-6bit | 6-bit | ≈ 9.6 GB | 16 GB+ | 108 |
| translategemma-12b-it-8bit | 8-bit | ≈ 12.5 GB | 16 GB+ | 1.1K |