MLX Community · First MLX build 21 Dec 2023
OpenHermes-2.5-Mistral-7B
MLX
Text apache-2.0
A 7.2B parameter text generation model, with 2 MLX builds at 4-bit.
- Parameters
- 7.2B From Hugging Face
- Quantisation
- Unstated OpenHermes-2.5-Mistral-7B
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 110 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Hugging Face does not list a weights size for this build, so there is no memory estimate.
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 · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/OpenHermes-2.5-Mistral-7B --prompt "Hello"MLX builds
2 on mlx-community| OpenHermes-2.5-Mistral-7B-4bit-mlx | 4-bit | 4.3 GB | 7 GB | 92 |
|---|---|---|---|---|
| OpenHermes-2.5-Mistral-7B | Unstated | — | — | 110 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.