mistral-community · First MLX build 6 Apr 2024
Mistral-7B-v0.2
MLX
apache-2.0
A 7.2B parameter model from mistral-community, with 3 MLX builds, from 4-bit to 8-bit.
- Parameters
- 7.2B From Hugging Face
- Quantisation
- Unstated dolphin-2.8-mistral-7b-v02
- Memory needed
- 19 GB Estimate, unified memory
- Download
- 14.5 GB Weights, estimated
- Downloads
- 53 This build, last 30 days
- Task
- —
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 19 GB at Unstated
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-2.8-mistral-7b-v02MLX builds
3 on mlx-community| dolphin-2.8-mistral-7b-v02-4bit | 4-bit | 4.3 GB | 7 GB | 46 |
|---|---|---|---|---|
| dolphin-2.8-mistral-7b-v02-8bit | 8-bit | 7.8 GB | 11 GB | 19 |
| dolphin-2.8-mistral-7b-v02 | Unstated | 14.5 GB | 19 GB | 53 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.