MXFP8 Open on Hugging Face
Parameters
30B
Weights (est.)
≈ 31.8 GB
Mac memory (est.)
48 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/GLM-4.7-Flash-abliterated-mxfp8 --prompt "Hello"
Details
- Base model
- huihui-ai/Huihui-GLM-4.7-Flash-abliterated (quantized)
- Vendor
- huihui-ai
- Task
- Text generation
- Quantisation
- MXFP8
- Licence
- mit
- Downloads
- 183 in the last 30 days · 2.1K all time · 2 likes
- Published
- 2026-03-07 · updated 2026-03-07 (8mo ago)
- Languages
- en, zh
- Tags
- glm4_moe_lite, abliterated, uncensored
Other MLX builds of huihui-ai/Huihui-GLM-4.7-Flash-abliterated
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| glm-4.7-flash-abliterated-8bit | 8-bit | ≈ 31.8 GB | 48 GB+ | 216 |
| GLM-4.7-Flash-abliterated-mxfp8 (this one) | MXFP8 | ≈ 31.8 GB | 48 GB+ | 183 |