Instructions to use mlx-community/Apertus-8B-2509-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/Apertus-8B-2509-4bit 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("mlx-community/Apertus-8B-2509-4bit") 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 mlx-community/Apertus-8B-2509-4bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "mlx-community/Apertus-8B-2509-4bit" --prompt "Once upon a time"
- Atomic Chat
- Xet hash:
- a74625a9077303173b54c1d8b2c1d5892e4aa82295067f5cc863aab19aa2a558
- Size of remote file:
- 4.53 GB
- SHA256:
- f039f9b2b8cb363607de50db269a2193243415ceb2ec66a456ee8ee15d953e09
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.