4-bit Open on Hugging Face
Parameters
73B
Weights (est.)
≈ 40.9 GB
Mac memory (est.)
48 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/magnum-v2-72b-4bit --prompt "Hello"
Details
- Base model
- anthracite-org/magnum-v2-72b (quantized)
- Vendor
- anthracite-org
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- tongyi-qianwen
- Downloads
- 60 in the last 30 days · 411 all time · 0 likes
- Published
- 2024-12-17 · updated 2024-12-17 (1y ago)
- Languages
- en, fr, de, es, it, pt, ru, zh, ja
- Tags
- qwen2, chat, model-index
Other MLX builds of anthracite-org/magnum-v2-72b
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| magnum-v2-72b-4bit (this one) | 4-bit | ≈ 40.9 GB | 48 GB+ | 60 |
| magnum-v2-72b | 8-bit | ≈ 77.3 GB | 96 GB+ | 72 |