Z.ai · First MLX build 30 Sept 2025
GLM-4.6
MLX
Text mit
A 353B parameter text generation model from Z.ai, with 3 MLX builds, from 4-bit to bf16.
- Parameters
- 353B From Hugging Face
- Quantisation
- 4-bit GLM-4.6-4bit
- Memory needed
- 224 GB Estimate, unified memory
- Download
- 199 GB Weights, estimated
- Downloads
- 355 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 224 GB at 4-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-4.6-4bit --prompt "Hello"MLX builds
3 on mlx-community| GLM-4.6-4bit | 4-bit | 199 GB | 224 GB | 355 |
|---|---|---|---|---|
| GLM-4.6-5bit | 5-bit | 243 GB | 274 GB | 104 |
| GLM-4.6-bf16 | bf16 | 706 GB | 791 GB | 42 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.