4-bit Open on Hugging Face
Parameters
15B
Weights (est.)
≈ 8.2 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/Unsloth-Phi-4-4bit --prompt "Hello"
Details
- Base model
- unsloth/phi-4 (quantized)
- Vendor
- unsloth
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- mit
- Downloads
- 126 in the last 30 days · 6.9K all time · 7 likes
- Published
- 2025-01-13 · updated 2025-01-13 (1y ago)
- Languages
- en
- Tags
- llama, phi4, unsloth, math, code, chat