MLX Community · First MLX build 7 Apr 2026
GLM-5.1
MLX
Text
A 744B parameter text generation model, with 3 MLX builds, from MXFP4 to MXFP8.
- Parameters
- 744B From Hugging Face
- Quantisation
- Unstated GLM-5.1
- Memory needed
- 1665 GB Estimate, unified memory
- Download
- 1488 GB Weights, estimated
- Downloads
- 457 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 1665 GB at Unstated
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-5.1 --prompt "Hello"MLX builds
3 on mlx-community| GLM-5.1-MXFP4-Q8 | MXFP4 | 419 GB | 470 GB | 222 |
|---|---|---|---|---|
| GLM-5.1 | Unstated | 1488 GB | 1665 GB | 457 |
| GLM-5.1-8bit-MXFP8 | MXFP8 | — | — | 21 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.