README.md

metadata

license: cc-by-4.0
language:
  - en
base_model: nvidia/OpenReasoning-Nemotron-32B
pipeline_tag: text-generation
library_name: mlx
tags:
  - nvidia
  - code
  - mlx

litmudoc/OpenReasoning-Nemotron-32B-MLX-Q4

This model litmudoc/OpenReasoning-Nemotron-32B-MLX-Q4 was converted to MLX format from nvidia/OpenReasoning-Nemotron-32B using mlx-lm version 0.26.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("litmudoc/OpenReasoning-Nemotron-32B-MLX-Q4")

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)