Modelpublic

nightmedia/Kimi-Linear-REAP-35B-A3B-Instruct-mxfp4-mlx

sourceHugging Facemitupdated 8mo agoView on Hugging Face

1likes192downloads

Model Card

Kimi-Linear-REAP-35B-A3B-Instruct-mxfp4-mlx

Updated model that works with the new transformers version coming soon

-G

This model Kimi-Linear-REAP-35B-A3B-Instruct-mxfp4-mlx was converted to MLX format from cerebras/Kimi-Linear-REAP-35B-A3B-Instruct using mlx-lm version 0.28.4.

Use with mlx

bash

pip install mlx-lm

python

from mlx_lm import load, generate

model, tokenizer = load("Kimi-Linear-REAP-35B-A3B-Instruct-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
    )

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