Mistral-Small-3.2-24B-Instruct-2506-8bit
mlx-community/Mistral-Small-3.2-24B-Instruct-2506-8bit
Text generation · mlx
8-bit Open on Hugging Face
Parameters
24B
Weights (est.)
≈ 25.0 GB
Mac memory (est.)
32 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-Small-3.2-24B-Instruct-2506-8bit --prompt "Hello"
Details
- Base model
- mistralai/Mistral-Small-3.2-24B-Instruct-2506 (quantized)
- Vendor
- Mistral
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- apache-2.0
- Downloads
- 823 in the last 30 days · 5.0K all time · 4 likes
- Published
- 2025-06-22 · updated 2025-06-22 (1y ago)
- Languages
- en, fr, de, es, pt, it, ja, ko, ru, zh, ar, fa, id, ms, ne, pl, ro, sr, sv, tr, uk, vi, hi, bn
- Tags
- mistral3
Other MLX builds of mistralai/Mistral-Small-3.2-24B-Instruct-2506
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Mistral-Small-3.2-24B-Instruct-2506-8bit (this one) | 8-bit | ≈ 25.0 GB | 32 GB+ | 823 |
| Mistral-Small-3.2-24B-Instruct-2506-bf16 | bf16 | ≈ 47.1 GB | 64 GB+ | 96 |