Views
No views yet
nvidia/Gemma-4-31B-IT-NVFP4.nvfp4 conversion for mlx-lm.pip install mlx-lm1from mlx_lm import load, generate
2
3model, tokenizer = load("KCh3dRi4n/Gemma-4-31B-IT-NVIDIA-NVFP4")
4
5prompt = "Hello"
6response = generate(model, tokenizer, prompt=prompt, max_tokens=64, verbose=True)
7print(response)