Instructions to use graelo/Devstral-Small-2507-4bits with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use graelo/Devstral-Small-2507-4bits with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("graelo/Devstral-Small-2507-4bits") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use graelo/Devstral-Small-2507-4bits with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "graelo/Devstral-Small-2507-4bits" --prompt "Once upon a time"
- Xet hash:
- 57821edc6fd99e42458405c38e3aa35a31643abf7a2595ba67f2e4c42717790a
- Size of remote file:
- 5.29 GB
- SHA256:
- 4d7e0e9904c600b1b6f3856ebdcf734b244b8294f7ec788b477035b3e818f3ea
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.