8-bit Open on Hugging Face
Parameters
127M
Weights (est.)
≈ 135 MB
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/lille-130m-instruct-8bit --prompt "Hello"
Details
- Base model
- mlx-community/lille-130m-instruct-fp16 (finetune)
- Vendor
- —
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- apache-2.0
- Downloads
- 25 in the last 30 days · 226 all time · 0 likes
- Published
- 2025-09-05 · updated 2025-09-05 (1y ago)
- Languages
- en
- Tags
- lille-130m, model-index
Other MLX builds of mlx-community/lille-130m-instruct-fp16
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| lille-130m-instruct-6bit | 6-bit | ≈ 103 MB | 8 GB+ | 30 |
| lille-130m-instruct-8bit (this one) | 8-bit | ≈ 135 MB | 8 GB+ | 25 |
| lille-130m-instruct-bf16 | bf16 | ≈ 254 MB | 8 GB+ | 118 |