Virtuoso-Small-4bit
mlx-community/Virtuoso-Small-4bit
Uncategorised · mlx
4-bit Open on Hugging Face
Parameters
15B
Weights (est.)
≈ 8.3 GB
Mac memory (est.)
16 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.
Details
- Base model
- arcee-ai/Virtuoso-Small (quantized)
- Vendor
- arcee-ai
- Task
- Uncategorised
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 12 in the last 30 days · 68 all time · 0 likes
- Published
- 2024-12-11 · updated 2024-12-11 (1y ago)
- Tags
- qwen2, model-index
Other MLX builds of arcee-ai/Virtuoso-Small
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Virtuoso-Small-4bit (this one) | 4-bit | ≈ 8.3 GB | 16 GB+ | 12 |
| Virtuoso-Small-6bit | 6-bit | ≈ 12.0 GB | 16 GB+ | 17 |
| Virtuoso-Small-8bit | 8-bit | ≈ 15.7 GB | 24 GB+ | 14 |