Phi-4-mini-instruct-mlx-4Bit
mlx-community/Phi-4-mini-instruct-mlx-4Bit
Text generation · transformers
4-bit Open on Hugging Face
Parameters
3.8B
Weights (est.)
≈ 2.2 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/Phi-4-mini-instruct-mlx-4Bit --prompt "Hello"
Details
- Base model
- microsoft/Phi-4-mini-instruct (quantized) · Phi 4 mini instruct on the radar →
- Vendor
- Microsoft · Phi
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- mit
- Downloads
- 475 in the last 30 days · 1.2K all time · 2 likes
- Published
- 2026-07-27 · updated 2026-07-27 (3mo ago)
- Languages
- multilingual, ar, zh, cs, da, nl, en, fi, fr, de, he, hu, it, ja, ko, no, pl, pt, ru, es, sv, th, tr, uk
- Tags
- phi3, code, mlx-my-repo, custom_code
Other MLX builds of microsoft/Phi-4-mini-instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Phi-4-mini-instruct-4bit | 4-bit | ≈ 2.2 GB | 8 GB+ | 2.6K |
| Phi-4-mini-instruct-mlx-4Bit (this one) | 4-bit | ≈ 2.2 GB | 8 GB+ | 475 |
| Phi-4-mini-instruct-6bit | 6-bit | ≈ 3.1 GB | 8 GB+ | 232 |
| Phi-4-mini-instruct-mlx-6Bit | 6-bit | ≈ 3.1 GB | 8 GB+ | 136 |
| Phi-4-mini-instruct-8bit | 8-bit | ≈ 4.1 GB | 8 GB+ | 758 |
| Phi-4-mini-instruct-mlx-8Bit | 8-bit | ≈ 4.1 GB | 8 GB+ | 248 |
| Phi-4-mini-instruct-mlx-fp16 | fp16 | ≈ 7.7 GB | 16 GB+ | 220 |