4-bit Open on Hugging Face
Parameters
8.2B
Weights (est.)
≈ 4.6 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/II-Medical-8B-4bit --prompt "Hello"
Details
- Base model
- Intelligent-Internet/II-Medical-8B (quantized)
- Vendor
- Intelligent-Internet
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- —
- Downloads
- 47 in the last 30 days · 536 all time · 0 likes
- Published
- 2025-06-04 · updated 2025-06-04 (1y ago)
- Tags
- qwen3
Other MLX builds of Intelligent-Internet/II-Medical-8B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| II-Medical-8B-4bit (this one) | 4-bit | ≈ 4.6 GB | 8 GB+ | 47 |
| II-Medical-8B-8bit | 8-bit | ≈ 8.7 GB | 16 GB+ | 37 |
| II-Medical-8B-bf16 | bf16 | ≈ 16.4 GB | 24 GB+ | 59 |