4-bit Open on Hugging Face
Parameters
24B
Weights (est.)
≈ 13.3 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/sarvam-m-4bit --prompt "Hello"
Details
- Base model
- sarvamai/sarvam-m (finetune)
- Vendor
- sarvamai
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 28 in the last 30 days · 259 all time · 0 likes
- Published
- 2025-05-27 · updated 2025-05-27 (1y ago)
- Languages
- en, bn, hi, kn, gu, mr, ml, or, pa, ta, te
- Tags
- mistral
Other MLX builds of sarvamai/sarvam-m
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| sarvam-m-mlx-3Bit | 3-bit | ≈ 10.3 GB | 16 GB+ | 31 |
| sarvam-m-4bit (this one) | 4-bit | ≈ 13.3 GB | 24 GB+ | 28 |
| sarvam-m-6bit | 6-bit | ≈ 19.2 GB | 24 GB+ | 21 |
| sarvam-m-8bit | 8-bit | ≈ 25.0 GB | 32 GB+ | 34 |
| sarvam-m-bf16 | bf16 | ≈ 47.1 GB | 64 GB+ | 23 |