MLX Community · First MLX build 14 Mar 2024
Hermes-2-Pro-Mistral-7B
MLX
apache-2.0
A 7.2B parameter model, with 2 MLX builds, from 4-bit to 8-bit.
- Parameters
- 7.2B From Hugging Face
- Quantisation
- 8-bit Hermes-2-Pro-Mistral-7B-8bit
- Memory needed
- 11 GB Estimate, unified memory
- Download
- 7.8 GB Weights, estimated
- Downloads
- 239 This build, last 30 days
- Task
- —
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 11 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/Hermes-2-Pro-Mistral-7B-8bitMLX builds
2 on mlx-community| Hermes-2-Pro-Mistral-7B-4bit | 4-bit | 4.3 GB | 7 GB | 199 |
|---|---|---|---|---|
| Hermes-2-Pro-Mistral-7B-8bit | 8-bit | 7.8 GB | 11 GB | 239 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.