MLX Community · First MLX build 1 Feb 2024
Mistral7B-Inst-v0.2-4bit-mlx-distilabel-capybara-dpo-7k
MLX
Text apache-2.0
A 3.7B parameter text generation model, with one MLX build at 4-bit.
- Parameters
- 3.7B From Hugging Face
- Quantisation
- 4-bit Mistral7B-Inst-v0.2-4bit-mlx-distilabel-capybara-dpo-7k
- Memory needed
- 5 GB Estimate, unified memory
- Download
- 2.3 GB Weights, estimated
- Downloads
- 113 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 5 GB at 4-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 · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/Mistral7B-Inst-v0.2-4bit-mlx-distilabel-capybara-dpo-7k --prompt "Hello"MLX builds
1 on mlx-community| Mistral7B-Inst-v0.2-4bit-mlx-distilabel-capybara-dpo-7k | 4-bit | 2.3 GB | 5 GB | 113 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.