gpt-oss-20b-no-think-mlx-Q8

SiddhJagani/gpt-oss-20b-mlx-8Bit

The Model SiddhJagani/gpt-oss-20b-mlx-8Bit was converted to MLX format from openai/gpt-oss-20b using mlx-lm version 0.28.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("SiddhJagani/gpt-oss-20b-mlx-Q8")

prompt = "hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    # Force our custom assistant marker
    prompt = force_generation_prompt(prompt)

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