Mistral-Large-4-1T-A52B-Text-4bit
mlx-community/Mistral-Large-4-1T-A52B-Text-4bit
Text generation · mlx
4-bit Open on Hugging Face
Parameters
1.0T
Weights (est.)
≈ 590 GB
Mac memory (est.)
> 512 GB
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/Mistral-Large-4-1T-A52B-Text-4bit --prompt "Hello"
Details
- Base model
- mistralai/Mistral-Large-4-1T-A52B (quantized) · Mistral Large 4 1T A52B on the radar →
- Vendor
- Mistral
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- mistral-ecosystem-open-weight-license
- Downloads
- 1.2K in the last 30 days · 1.2K all time · 1 likes
- Published
- 2026-10-29 · updated 2026-10-29 (13d ago)
- Tags
- mistral_large4
Other MLX builds of mistralai/Mistral-Large-4-1T-A52B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Mistral-Large-4-1T-A52B-Text-2bit | 2-bit | ≈ 328 GB | 512 GB+ | 1.1K |
| Mistral-Large-4-1T-A52B-Text-3bit | 3-bit | ≈ 459 GB | > 512 GB | 874 |
| Mistral-Large-4-1T-A52B-Text-4bit (this one) | 4-bit | ≈ 590 GB | > 512 GB | 1.2K |