NousResearch · First MLX build 13 Dec 2024
Hermes-2-Pro-Mistral-7B
MLX
apache-2.0
A 7.2B parameter model from NousResearch, with one MLX build at 3-bit.
- Parameters
- 7.2B From Hugging Face
- Quantisation
- 3-bit Hermes-2-Pro-Mistral-7B-3bit
- Memory needed
- 6 GB Estimate, unified memory
- Download
- 3.2 GB Weights, estimated
- Downloads
- 101 This build, last 30 days
- Task
- —
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 6 GB at 3-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/Hermes-2-Pro-Mistral-7B-3bitMLX builds
1 on mlx-community| Hermes-2-Pro-Mistral-7B-3bit | 3-bit | 3.2 GB | 6 GB | 101 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.