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/phi-4-abliterated-4bit --prompt "Hello"
Details
- Base model
- huihui-ai/phi-4-abliterated
- Vendor
- huihui-ai
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- mit
- Downloads
- 107 in the last 30 days · 1.1K all time · 1 likes
- Published
- 2025-01-09 · updated 2025-01-09 (1y ago)
- Languages
- en
- Tags
- phi3, math, code, chat, abliterated, uncensored, mlx-my-repo, custom_code
Other MLX builds of huihui-ai/phi-4-abliterated
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| phi-4-abliterated-2bit | 2-bit | ≈ 4.6 GB | 8 GB+ | 49 |
| phi-4-abliterated-3bit | 3-bit | ≈ 6.4 GB | 16 GB+ | 39 |
| phi-4-abliterated-4bit (this one) | 4-bit | ≈ 8.2 GB | 16 GB+ | 107 |
| phi-4-abliterated-6bit | 6-bit | ≈ 11.9 GB | 16 GB+ | 34 |
| phi-4-abliterated-8bit | 8-bit | ≈ 15.6 GB | 24 GB+ | 36 |