sunfall-nemomix-unleashed-12b-v0.6.1-8bit
mlx-community/sunfall-nemomix-unleashed-12b-v0.6.1-8bit
Text generation · transformers
8-bit Open on Hugging Face
Parameters
3.4B
Weights (est.)
≈ 4.0 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/sunfall-nemomix-unleashed-12b-v0.6.1-8bit --prompt "Hello"
Details
- Base model
- mistralai/Mistral-Nemo-Instruct-2407 (quantized)
- Vendor
- Mistral
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- —
- Downloads
- 33 in the last 30 days · 212 all time · 2 likes
- Published
- 2025-02-22 · updated 2025-02-22 (1y ago)
- Tags
- mistral, not-for-all-audiences
Other MLX builds of mistralai/Mistral-Nemo-Instruct-2407
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| sunfall-nemomix-unleashed-12b-v0.6.1-8bit (this one) | 8-bit | ≈ 4.0 GB | 8 GB+ | 33 |
| Mistral-Nemo-Instruct-2407-3bit | 3-bit | ≈ 5.4 GB | 8 GB+ | 54 |