Mistral AI · First MLX build 29 Oct 2026
Mistral-Large-4-1T-A52B
MLX
Text mistral-ecosystem-open-weight-license New
A 1.0T parameter text generation model from Mistral AI, with 3 MLX builds, from 2-bit to 4-bit.
- Parameters
- 1.0T From Hugging Face
- Quantisation
- 4-bit Mistral-Large-4-1T-A52B-Text-4bit
- Memory needed
- 662 GB Estimate, unified memory
- Download
- 590 GB Weights, estimated
- Downloads
- 1.2K 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 662 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/Mistral-Large-4-1T-A52B-Text-4bit --prompt "Hello"MLX builds
3 on mlx-community| Mistral-Large-4-1T-A52B-Text-2bit | 2-bit | 328 GB | 369 GB | 1.1K |
|---|---|---|---|---|
| Mistral-Large-4-1T-A52B-Text-3bit | 3-bit | 459 GB | 516 GB | 901 |
| Mistral-Large-4-1T-A52B-Text-4bit | 4-bit | 590 GB | 662 GB | 1.2K |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.