4-bit Open on Hugging Face
Parameters
2.5B
Weights (est.)
≈ 1.4 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-1-4bit --prompt "Hello"
Details
- Base model
- sarvamai/sarvam-1 (quantized)
- Vendor
- sarvamai
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- —
- Downloads
- 52 in the last 30 days · 790 all time · 1 likes
- Published
- 2024-10-24 · updated 2024-10-24 (2y ago)
- Languages
- bn, en, gu, hi, kn, ml, mr, or, pa, ta, te
- Tags
- llama