How to use from the
Use from the
MLX library
# Download the model from the Hub
pip install huggingface_hub[hf_xet]

huggingface-cli download --local-dir Qwen3-Compliance-Medical-v1 AdrianReiter/Qwen3-Compliance-Medical-v1

Qwen3 Compliance Medical Agent (v1)

This model is a fine-tuned version of Qwen3-0.6B specialized in Medical Device Regulation (ISO 13485, IEC 62304, ISO 14971).

๐Ÿ’ป How to use

With MLX (Apple Silicon)

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("AdrianReiter/Qwen3-Compliance-Medical-v1")

prompt = """<|im_start|>system
You are a Regulatory Consultant. Always analyze dependencies and risk before answering.<|im_end|>
<|im_start|>user
We want to use an open-source library in our device. What are the risks?<|im_end|>
<|im_start|>assistant
"""

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

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "AdrianReiter/Qwen3-Compliance-Medical-v1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

# ... use standard pipeline ...
Downloads last month
19
Safetensors
Model size
0.6B params
Tensor type
BF16
ยท
MLX
Hardware compatibility
Log In to add your hardware

Quantized

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for AdrianReiter/Qwen3-Compliance-Medical-v1

Finetuned
Qwen/Qwen3-0.6B
Finetuned
(1155)
this model