Modelpublic

nightmedia/Mistral-Nemo-Instruct-2407-12B-Thinking-HI-Claude-Opus-High-Reasoning-mxfp4-mlx

sourceHugging Faceupdated 9mo agoView on Hugging Face

0likes153downloads

Model Card

Mistral-Nemo-Instruct-2407-12B-Thinking-HI-Claude-Opus-High-Reasoning-mxfp4-mlx

Brainwaves

HI-mxfp4  0.457,0.592,0.806,0.726,0.438,0.789,0.706
M-mxfp4   0.457,0.591,0.786,0.724,0.428,0.793,0.712

This model Mistral-Nemo-Instruct-2407-12B-Thinking-HI-Claude-Opus-High-Reasoning-mxfp4-mlx was converted to MLX format from DavidAU/Mistral-Nemo-Instruct-2407-12B-Thinking-HI-Claude-Opus-High-Reasoning using mlx-lm version 0.30.0.

Use with mlx

bash

pip install mlx-lm

python

from mlx_lm import load, generate

model, tokenizer = load("Mistral-Nemo-Instruct-2407-12B-Thinking-HI-Claude-Opus-High-Reasoning-mxfp4-mlx")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True, return_dict=False,
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)