MLX Community · First MLX build 23 Nov 2025
GLM-4.6
MLX
Text mit
A 353B parameter text generation model, with 2 MLX builds, from 6-bit to 8-bit.
- Parameters
- 353B From Hugging Face
- Quantisation
- 8-bit GLM-4.6-8bit
- Memory needed
- 422 GB Estimate, unified memory
- Download
- 375 GB Weights, estimated
- Downloads
- 33 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 422 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-4.6-8bit --prompt "Hello"MLX builds
2 on mlx-community| GLM-4.6-6bit | 6-bit | 287 GB | 323 GB | 26 |
|---|---|---|---|---|
| GLM-4.6-8bit | 8-bit | 375 GB | 422 GB | 33 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.