Instructions to use hkust-aaron/EdgeRock-4B-MLX-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use hkust-aaron/EdgeRock-4B-MLX-8bit 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("hkust-aaron/EdgeRock-4B-MLX-8bit") 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 hkust-aaron/EdgeRock-4B-MLX-8bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "hkust-aaron/EdgeRock-4B-MLX-8bit" --prompt "Once upon a time"
- Atomic Chat
Commit History
2 days ago
-
docs: add Rock Matrix website and organize model navigation
Verified signatureAdd the official rockmatrix.ai link and clarify model navigation. Main model cards list the complete EdgeRock family. Variant cards show their own installation and validation before original-model benchmark context. Only README files change; weights, runtime code, benchmark values, reports, and license files are preserved.fdb94d3
4 days ago
-
Expand model card with full EdgeRock overview and release-specific deployment guide
Verified signature353fd00 -
Publish validated EdgeRock runtime conversion and complete launch package
Verified signature4a8f623 -
initial commit
Verified signature346828d