TeichAI · First MLX build 15 Feb 2026
GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill
MLX
Text apache-2.0
A 30B parameter text generation model from TeichAI, with 5 MLX builds, from 4-bit to 8-bit.
- Parameters
- 30B From Hugging Face
- Quantisation
- 4-bit GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-4bit
- Memory needed
- 21 GB Estimate, unified memory
- Download
- 16.9 GB Weights, estimated
- Downloads
- 193 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 5 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 21 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-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-4bit --prompt "Hello"MLX builds
5 on mlx-community| GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-4bit | 4-bit | 16.9 GB | 21 GB | 193 |
|---|---|---|---|---|
| GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-mxfp4 | MXFP4 | 16.9 GB | 21 GB | 91 |
| GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-6bit | 6-bit | 24.3 GB | 30 GB | 116 |
| GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-8bit | 8-bit | 31.8 GB | 38 GB | 91 |
| GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-bfloat16 | Unstated | 59.9 GB | 69 GB | 88 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.