Z.ai · First MLX build 12 Feb 2026
GLM-5
MLX
Text mit
A 744B parameter text generation model from Z.ai, with 3 MLX builds, from 4-bit to MXFP4.
- Parameters
- 744B From Hugging Face
- Quantisation
- 4-bit GLM-5-4bit
- Memory needed
- 470 GB Estimate, unified memory
- Download
- 419 GB Weights, estimated
- Downloads
- 221 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 470 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-5-4bit --prompt "Hello"MLX builds
3 on mlx-community| GLM-5-4bit | 4-bit | 419 GB | 470 GB | 221 |
|---|---|---|---|---|
| GLM-5-MXFP4-Q8 | MXFP4 | 419 GB | 470 GB | 104 |
| GLM-5 | Unstated | 1488 GB | 1665 GB | 119 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.