MLX Community · First MLX build 7 Mar 2026
glm-4.7-flash-abliterated
MLX
Text mit
A 30B parameter text generation model, with 2 MLX builds, from 8-bit to MXFP8.
- Parameters
- 30B From Hugging Face
- Quantisation
- 8-bit glm-4.7-flash-abliterated-8bit
- Memory needed
- 38 GB Estimate, unified memory
- Download
- 31.8 GB Weights, estimated
- Downloads
- 209 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 38 GB at 8-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/glm-4.7-flash-abliterated-8bit --prompt "Hello"MLX builds
2 on mlx-community| glm-4.7-flash-abliterated-8bit | 8-bit | 31.8 GB | 38 GB | 209 |
|---|---|---|---|---|
| GLM-4.7-Flash-abliterated-mxfp8 | MXFP8 | 31.8 GB | 38 GB | 174 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.