MLX Community · First MLX build 20 Dec 2023
Mistral-7B-Instruct-v0.2
MLX
Text apache-2.0
A 7.2B parameter text generation model, with 5 MLX builds, from 4-bit to 8-bit.
- Parameters
- 7.2B From Hugging Face
- Quantisation
- 4-bit Mistral-7B-Instruct-v0.2-4-bit
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 850 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 5 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/Mistral-7B-Instruct-v0.2-4-bit --prompt "Hello"MLX builds
5 on mlx-community| Mistral-7B-Instruct-v0.2-4bit | 4-bit | 4.3 GB | 7 GB | 301 |
|---|---|---|---|---|
| Mistral-7B-Instruct-v0.2-4-bit | 4-bit | — | — | 850 |
| Mistral-7B-Instruct-v0.2 | Unstated | — | — | 445 |
| Mistral-7B-Instruct-v0.2-8-bit-mlx | 8-bit | — | — | 57 |
| Mistral-7B-Instruct-v0.2-4bit-mlx | 4-bit | — | — | 52 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.