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.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/MagenticBrain-4bit --prompt "Hello"
Details
- Base model
- microsoft/MagenticBrain (quantized)
- Vendor
- Microsoft · Phi
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- mit
- Downloads
- 106 in the last 30 days · 1.2K all time · 1 likes
- Published
- 2026-07-29 · updated 2026-07-29 (3mo ago)
- Languages
- en
- Tags
- qwen3, agent, agentic, tool-use, function-calling, orchestration, magentic
Other MLX builds of microsoft/MagenticBrain
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| MagenticBrain-4bit (this one) | 4-bit | ≈ 8.3 GB | 16 GB+ | 106 |
| MagenticBrain-8bit | 8-bit | ≈ 15.7 GB | 24 GB+ | 34 |