3-bit Open on Hugging Face
Parameters
7.6B
Weights (est.)
≈ 3.3 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/Qwen2.5-7B-Medicine-3bit --prompt "Hello"
Details
- Base model
- WangCa/Qwen2.5-7B-Medicine (quantized)
- Vendor
- WangCa
- Task
- Text generation
- Quantisation
- 3-bit
- Licence
- mit
- Downloads
- 26 in the last 30 days · 313 all time · 0 likes
- Published
- 2025-06-14 · updated 2025-06-14 (1y ago)
- Languages
- zh
- Tags
- qwen2, medical
Other MLX builds of WangCa/Qwen2.5-7B-Medicine
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Qwen2.5-7B-Medicine-3bit (this one) | 3-bit | ≈ 3.3 GB | 8 GB+ | 26 |
| Qwen2.5-7B-Medicine-4bit | 4-bit | ≈ 4.3 GB | 8 GB+ | 72 |