4-bit Open on Hugging Face
Parameters
33B
Weights (est.)
≈ 18.4 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/Virtuoso-Medium-v2-4bit --prompt "Hello"
Details
- Base model
- arcee-ai/Virtuoso-Medium-v2 (quantized)
- Vendor
- arcee-ai
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 38 in the last 30 days · 259 all time · 0 likes
- Published
- 2025-01-30 · updated 2025-01-30 (1y ago)
- Tags
- qwen2, mergekit, merge
Other MLX builds of arcee-ai/Virtuoso-Medium-v2
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Virtuoso-Medium-v2-3bit | 3-bit | ≈ 14.3 GB | 24 GB+ | 38 |
| Virtuoso-Medium-v2-4bit (this one) | 4-bit | ≈ 18.4 GB | 24 GB+ | 38 |
| Virtuoso-Medium-v2-6bit | 6-bit | ≈ 26.6 GB | 32 GB+ | 29 |
| Virtuoso-Medium-v2-8bit | 8-bit | ≈ 34.8 GB | 48 GB+ | 26 |
| Virtuoso-Medium-v2-bf16 | bf16 | ≈ 65.5 GB | 96 GB+ | 17 |