Mistral-Small-24B-Instruct-2501-4bit
mlx-community/Mistral-Small-24B-Instruct-2501-4bit
Uncategorised · vllm
4-bit Open on Hugging Face
Parameters
24B
Weights (est.)
≈ 13.3 GB
Mac memory (est.)
24 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.
Details
- Base model
- mistralai/Mistral-Small-24B-Instruct-2501 (quantized)
- Vendor
- Mistral
- Task
- Uncategorised
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 787 in the last 30 days · 16K all time · 15 likes
- Published
- 2025-01-30 · updated 2025-01-30 (1y ago)
- Languages
- en, fr, de, es, it, pt, zh, ja, ru, ko
- Tags
- vllm, mistral
Other MLX builds of mistralai/Mistral-Small-24B-Instruct-2501
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Mistral-Small-24B-Instruct-2501-3bit | 3-bit | ≈ 10.3 GB | 16 GB+ | 114 |
| Mistral-Small-24B-Instruct-2501-4bit (this one) | 4-bit | ≈ 13.3 GB | 24 GB+ | 787 |
| Mistral-Small-24B-Instruct-2501-6bit | 6-bit | ≈ 19.2 GB | 24 GB+ | 34 |
| Mistral-Small-24B-Instruct-2501-8bit | 8-bit | ≈ 25.0 GB | 32 GB+ | 81 |
| Mistral-Small-24B-Instruct-2501-bf16 | bf16 | ≈ 47.1 GB | 64 GB+ | 143 |