Instructions to use Youssofal/Gemma4-MTPLX-Optimized-Speed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Youssofal/Gemma4-MTPLX-Optimized-Speed 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("Youssofal/Gemma4-MTPLX-Optimized-Speed") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
- MLX LM
How to use Youssofal/Gemma4-MTPLX-Optimized-Speed with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "Youssofal/Gemma4-MTPLX-Optimized-Speed" --prompt "Once upon a time"
| { | |
| "artifact_schema": "mtplx.gemma4.google.v1", | |
| "config.json_sha256": "b2a7c25dc48e584d3debc824534a62cd73a801108b1cc7a15d32676195d7f03a", | |
| "created_at_unix": 1778037794, | |
| "generation_config.json_sha256": "d4226bbe3117d2d253ba4609720ba82c6c4ce4627a9a6ae05387c78983ac03de", | |
| "quantization": { | |
| "bits": 4, | |
| "format": "mlx-flat4-g64", | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "role": "target", | |
| "source_repo": "google/gemma-4-31B-it", | |
| "source_revision": "145dc2508c480a64b47242f160d286cff94a2343", | |
| "source_snapshot": "/Users/youssof/Documents/MTPLX/models/.sources/gemma-4-31B-it-145dc2508c48", | |
| "tokenizer.json_sha256": "cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f", | |
| "tokenizer_config.json_sha256": "a284d1243b62be31faa9c13e1c28cece940c4abaa7bd9ad87b94f61b40687200" | |
| } | |