dphn · First MLX build 19 Jun 2025
Dolphin-Mistral-24B-Venice-Edition
MLX
Text apache-2.0
A 24B parameter text generation model from dphn, with 5 MLX builds, from 4-bit to 8-bit.
- Parameters
- 24B From Hugging Face
- Quantisation
- 8-bit Dolphin-Mistral-24B-Venice-Edition-mlx-8Bit
- Memory needed
- 30 GB Estimate, unified memory
- Download
- 25.0 GB Weights, estimated
- Downloads
- 741 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 5 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 30 GB at 8-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/Dolphin-Mistral-24B-Venice-Edition-mlx-8BitMLX builds
5 on mlx-community| Dolphin-Mistral-24B-Venice-Edition-DWQ | 4-bit | 13.3 GB | 17 GB | 385 |
|---|---|---|---|---|
| Dolphin-Mistral-24B-Venice-Edition-4bit | 4-bit | 13.3 GB | 17 GB | 255 |
| Dolphin-Mistral-24B-Venice-Edition-5bit | 5-bit | 16.2 GB | 21 GB | 64 |
| Dolphin-Mistral-24B-Venice-Edition-6bit | 6-bit | 19.2 GB | 24 GB | 145 |
| Dolphin-Mistral-24B-Venice-Edition-mlx-8Bit | 8-bit | 25.0 GB | 30 GB | 741 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.