Converted from utter-project/EuroLLM-22B-Instruct-2512 using mlx_lm.convert with --q-mode nvfp4 --q-group-size 16 on 2026-03-05, 22:07.
- Downloads last month
- 27
Model size
23B params
Tensor type
U8
路
U32 路
BF16 路
Hardware compatibility
Log In to add your hardware
4-bit
Model tree for dumtjul/EuroLLM-22B-Instruct-2512-mlx-nvfp4
Base model
utter-project/EuroLLM-22B-2512 Finetuned
utter-project/EuroLLM-22B-Instruct-2512
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("dumtjul/EuroLLM-22B-Instruct-2512-mlx-nvfp4") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True)