4-bit Open on Hugging Face
Parameters
8.0B
Weights (est.)
≈ 4.5 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/UserLM-8b-4bit --prompt "Hello"
Details
- Base model
- microsoft/UserLM-8b (quantized)
- Vendor
- Microsoft · Phi
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- mit
- Downloads
- 35 in the last 30 days · 243 all time · 0 likes
- Published
- 2025-10-09 · updated 2025-10-09 (1y ago)
- Languages
- en
- Tags
- llama, userlm, simulation, mlx-my-repo
Other MLX builds of microsoft/UserLM-8b
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| UserLM-8b-4bit (this one) | 4-bit | ≈ 4.5 GB | 8 GB+ | 35 |
| UserLM-8b-6bit | 6-bit | ≈ 6.5 GB | 16 GB+ | 33 |
| UserLM-8b-8bit | 8-bit | ≈ 8.5 GB | 16 GB+ | 33 |