Dolphin3.0-R1-Mistral-24B-4bit
mlx-community/Dolphin3.0-R1-Mistral-24B-4bit
Text generation · transformers
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/Dolphin3.0-R1-Mistral-24B-4bit --prompt "Hello"
Details
- Base model
- dphn/Dolphin3.0-R1-Mistral-24B (quantized)
- Vendor
- dphn
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- —
- Downloads
- 487 in the last 30 days · 4.5K all time · 2 likes
- Published
- 2025-02-16 · updated 2025-02-16 (1y ago)
- Languages
- en
- Tags
- mistral
Other MLX builds of dphn/Dolphin3.0-R1-Mistral-24B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Dolphin3.0-R1-Mistral-24B-4bit (this one) | 4-bit | ≈ 13.3 GB | 24 GB+ | 487 |
| Dolphin3.0-R1-Mistral-24B-6bit | 6-bit | ≈ 19.2 GB | 24 GB+ | 54 |