pip install mlx-lm

from mlx_lm import load, generate

# Load model (from HF hub or local path)
model, tokenizer = load("mlx-community/Llama-3.2-3B-Instruct-4bit")

# Generate text
response = generate(
    model,
    tokenizer,
    prompt="Explain quantum computing in simple terms:",
    max_tokens=256,
    temp=0.7,
)
print(response)

from mlx_lm import load, stream_generate

model, tokenizer = load("mlx-community/Mistral-7B-Instruct-v0.3-4bit")

prompt = "Write a haiku about programming:"
for response in stream_generate(model, tokenizer, prompt, max_tokens=100):
    print(response.text, end="", flush=True)
print()

from mlx_lm import load, batch_generate

model, tokenizer = load("mlx-community/Qwen2.5-7B-Instruct-4bit")

prompts = [
    "What is machine learning?",
    "Explain neural networks:",
    "Define deep learning:",
]

responses = batch_generate(
    model,
    tokenizer,
    prompts,
    max_tokens=100,
)

for prompt, response in zip(prompts, responses):
    print(f"Q: {prompt}\nA: {response}\n")

# Basic generation
mlx_lm.generate --model mlx-community/Llama-3.2-3B-Instruct-4bit \
    --prompt "Explain recursion:" \
    --max-tokens 256

# With sampling parameters
mlx_lm.generate --model mlx-community/Mistral-7B-Instruct-v0.3-4bit \
    --prompt "Write a poem about AI:" \
    --temp 0.8 \
    --top-p 0.95

# Start chat REPL (context preserved between turns)
mlx_lm.chat --model mlx-community/Llama-3.2-3B-Instruct-4bit

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Llama-3.2-3B-Instruct-4bit")

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "What's the capital of France?"},
]

prompt = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

response = generate(model, tokenizer, prompt=prompt, max_tokens=256)
print(response)

# Convert with 4-bit quantization
mlx_lm.convert --hf-path meta-llama/Llama-3.2-3B-Instruct \
    -q  # Quantize to 4-bit

# With specific quantization
mlx_lm.convert --hf-path mistralai/Mistral-7B-Instruct-v0.3 \
    -q \
    --q-bits 8 \
    --q-group-size 64

# Upload to Hugging Face Hub
mlx_lm.convert --hf-path meta-llama/Llama-3.2-1B-Instruct \
    -q \
    --upload-repo your-username/Llama-3.2-1B-Instruct-4bit-mlx

from mlx_lm import convert

convert(
    hf_path="meta-llama/Llama-3.2-3B-Instruct",
    mlx_path="./llama-3.2-3b-mlx",
    quantize=True,
    q_bits=4,
    q_group_size=64,
)

# 4-bit quantization during conversion
mlx_lm.convert --hf-path mistralai/Mistral-7B-v0.3 -q

# 8-bit for higher quality
mlx_lm.convert --hf-path mistralai/Mistral-7B-v0.3 -q --q-bits 8

# Prepare training data (JSONL format)
# {"text": "Your training text here"}
# or
# {"messages": [{"role": "user", "content": "..."}, {"role": "assistant", "content": "..."}]}

# Fine-tune with LoRA
mlx_lm.lora --model mlx-community/Llama-3.2-3B-Instruct-4bit \
    --train \
    --data ./data \
    --iters 1000

# Generate with adapter
mlx_lm.generate --model mlx-community/Llama-3.2-3B-Instruct-4bit \
    --adapter-path ./adapters \
    --prompt "Your prompt here"

# Merge LoRA weights into base model
mlx_lm.fuse --model mlx-community/Llama-3.2-3B-Instruct-4bit \
    --adapter-path ./adapters \
    --save-path ./fused-model

# Or export to GGUF
mlx_lm.fuse --model mlx-community/Llama-3.2-3B-Instruct-4bit \
    --adapter-path ./adapters \
    --export-gguf

# Start server
mlx_lm.server --model mlx-community/Llama-3.2-3B-Instruct-4bit --port 8080

# Use with OpenAI client
curl http://localhost:8080/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
        "model": "default",
        "messages": [{"role": "user", "content": "Hello!"}],
        "max_tokens": 256
    }'

from openai import OpenAI

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

response = client.chat.completions.create(
    model="default",
    messages=[{"role": "user", "content": "Explain MLX in one sentence."}],
    max_tokens=100,
)
print(response.choices[0].message.content)