MLX

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'http://localhost:8080/v1',
  apiKey: 'not-needed'
})

const response = await client.chat.completions.create({
  model: 'mlx-community/Qwen3-8B-4bit',
  messages: [{ role: 'user', content: 'Explain closures in one paragraph.' }]
})

console.log(response.choices[0].message.content)

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:8080/v1",
    api_key="not-needed",
)

response = client.chat.completions.create(
    model="mlx-community/Qwen3-8B-4bit",
    messages=[{"role": "user", "content": "Explain closures in one paragraph."}],
)

print(response.choices[0].message.content)

curl http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mlx-community/Qwen3-8B-4bit",
    "messages": [{"role": "user", "content": "Explain closures in one paragraph."}]
  }'

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen3-8B-4bit")

prompt = tokenizer.apply_chat_template(
    [{"role": "user", "content": "Explain closures in one paragraph."}],
    add_generation_prompt=True,
)

print(generate(model, tokenizer, prompt=prompt, max_tokens=512))