Dolphin-Mistral-24B-Venice-Edition-DWQ
mlx-community/Dolphin-Mistral-24B-Venice-Edition-DWQ
Text generation · mlx
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/Dolphin-Mistral-24B-Venice-Edition-DWQ --prompt "Hello"
Details
- Base model
- dphn/Dolphin-Mistral-24B-Venice-Edition (quantized)
- Vendor
- dphn
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 389 in the last 30 days · 4.2K all time · 5 likes
- Published
- 2025-07-07 · updated 2025-07-07 (1y ago)
- Tags
- mistral
Other MLX builds of dphn/Dolphin-Mistral-24B-Venice-Edition
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Dolphin-Mistral-24B-Venice-Edition-DWQ (this one) | 4-bit | ≈ 13.3 GB | 24 GB+ | 389 |
| Dolphin-Mistral-24B-Venice-Edition-4bit | 4-bit | ≈ 13.3 GB | 24 GB+ | 250 |
| Dolphin-Mistral-24B-Venice-Edition-5bit | 5-bit | ≈ 16.2 GB | 24 GB+ | 65 |
| Dolphin-Mistral-24B-Venice-Edition-6bit | 6-bit | ≈ 19.2 GB | 24 GB+ | 141 |
| Dolphin-Mistral-24B-Venice-Edition-mlx-8Bit | 8-bit | ≈ 25.0 GB | 32 GB+ | 746 |