Mistral-Small-24B-Instruct-2501-abliterated-4-bit
mlx-community/Mistral-Small-24B-Instruct-2501-abliterated-4-bit
Text generation · 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.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/Mistral-Small-24B-Instruct-2501-abliterated-4-bit --prompt "Hello"
Details
- Base model
- huihui-ai/Mistral-Small-24B-Instruct-2501-abliterated
- Vendor
- huihui-ai
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 176 in the last 30 days · 1.9K all time · 1 likes
- Published
- 2025-02-20 · updated 2025-02-20 (1y ago)
- Languages
- en, fr, de, es, it, pt, zh, ja, ru, ko
- Tags
- vllm, mistral, abliterated, uncensored
Other MLX builds of huihui-ai/Mistral-Small-24B-Instruct-2501-abliterated
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Mistral-Small-24B-Instruct-2501-abliterated-4-bit (this one) | 4-bit | ≈ 13.3 GB | 24 GB+ | 176 |
| Mistral-Small-24B-Instruct-2501-abliterated-8-bit | 8-bit | ≈ 25.0 GB | 32 GB+ | 140 |
| Mistral-Small-24B-Instruct-2501-abliterated | — | ≈ 47.1 GB | 64 GB+ | 86 |