4-bit Open on Hugging Face
Parameters
27B
Weights (est.)
≈ 15.2 GB
Mac memory (est.)
24 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-27b-it-4bit --prompt "Hello"
Details
- Base model
- google/translategemma-27b-it (quantized)
- Vendor
- Google · Gemma
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- gemma
- Downloads
- 698 in the last 30 days · 4.4K all time · 4 likes
- Published
- 2026-01-15 · updated 2026-01-16 (9mo ago)
- Tags
- gemma3
Other MLX builds of google/translategemma-27b-it
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| translategemma-27b-it-4bit (this one) | 4-bit | ≈ 15.2 GB | 24 GB+ | 698 |
| translategemma-27b-it-6bit | 6-bit | ≈ 21.9 GB | 32 GB+ | 131 |
| translategemma-27b-it-8bit | 8-bit | ≈ 28.7 GB | 48 GB+ | 359 |
| translategemma-27b-it-bf16 | bf16 | ≈ 54.0 GB | 64 GB+ | 103 |