cagataydev/Qwen3.5-4B-cagatay-4bit

pip install strands-agents strands-agents-mlx

from strands import Agent
from strands_mlx import MLXModel

# Load the 4-bit quantized model
model = MLXModel(model_id="cagataydev/Qwen3.5-4B-cagatay-4bit")

# Create an agent with tools
agent = Agent(model=model)

# Use it!
agent("Plan the steps to pick up a red cube and place it on the shelf")

from strands import Agent, tool
from strands_mlx import MLXModel

@tool
def get_robot_state() -> dict:
    """Get the current state of the robot."""
    return {"position": [0.5, 0.3, 0.1], "gripper": "open"}

model = MLXModel(
    model_id="cagataydev/Qwen3.5-4B-cagatay-4bit",
    params={"temperature": 0.7, "max_tokens": 1024}
)

agent = Agent(model=model, tools=[get_robot_state])
agent("What is the robot's current position? Then plan a pick-and-place task.")

pip install devduck
export MODEL_PROVIDER=mlx
export STRANDS_MODEL_ID=cagataydev/Qwen3.5-4B-cagatay-4bit
devduck

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("cagataydev/Qwen3.5-4B-cagatay-4bit")

messages = [{"role": "user", "content": "Plan how to pick up a cup from the table"}]
prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_dict=False)

response = generate(model, tokenizer, prompt=prompt, verbose=True, max_tokens=512)

mlx_lm generate --model cagataydev/Qwen3.5-4B-cagatay-4bit --prompt "Hello!"