from mlx_lm import load, generate

model, tokenizer = load("minimax-reap50-mlx-4bit")

response = generate(
    model, 
    tokenizer, 
    prompt="Write a function to calculate fibonacci numbers",
    max_tokens=500,
    verbose=True
)
print(response)

mlx.server

Start the server:

mlx_lm.server --model minimax-reap50-mlx-4bit --port 8080

Make requests:

bash

curl -X POST http://localhost:8080/v1/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "default_model",
    "prompt": "Write a function to calculate fibonacci numbers",
    "max_tokens": 500
  }'

Or use the chat endpoint:

bash

curl -X POST http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "default_model",
    "messages": [
      {"role": "user", "content": "Write a function to calculate fibonacci numbers"}
    ],
    "max_tokens": 500
  }'

Trade-offs

Memory: Lowest memory footprint (~65.5 GB)
Quality: Acceptable quality with minor degradation
Speed: Fastest inference speed

AlexGS74/MiniMax-M2.1-REAP-50-mlx-4bit

MiniMax REAP-50 MLX 4-bit

Quantization Details

Usage

Python

mlx.server

Trade-offs

AlexGS74/
MiniMax-M2.1-REAP-50-mlx-4bit