4-bit Open on Hugging Face
Parameters
4.6B
Weights (est.)
≈ 2.6 GB
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/sarvam-translate-mlx-4bit --prompt "Hello"
Details
- Base model
- sarvamai/sarvam-translate (quantized)
- Vendor
- sarvamai
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- gpl-3.0
- Downloads
- 59 in the last 30 days · 789 all time · 2 likes
- Published
- 2025-06-18 · updated 2025-06-19 (1y ago)
- Languages
- as, bn, brx, doi, gom, gu, en, hi, kn, ks, mai, ml, mni, mr, ne, or, pa, sa, sat, sd, ta, te, ur
- Tags
- gemma3
Other MLX builds of sarvamai/sarvam-translate
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| sarvam-translate-mlx-4bit (this one) | 4-bit | ≈ 2.6 GB | 8 GB+ | 59 |
| sarvam-translate-mlx-bf16 | bf16 | ≈ 9.1 GB | 16 GB+ | 24 |