from vllm import LLM, SamplingParams

# Initialize the model
llm = LLM(
    model="HarleyWang/Qwen3.5-27B-Claude-Opus-4.6-High-Reasoning",
    dtype="bfloat16",
    tensor_parallel_size=2,  # Adjust based on your GPU count
    max_model_len=8192,
)

# Define sampling parameters
sampling_params = SamplingParams(
    temperature=0.7,
    top_p=0.9,
    max_tokens=2048,
)

# Create messages
messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Explain how to optimize a slow database query."}
]

# Use apply_chat_template from tokenizer
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("HarleyWang/Qwen3.5-27B-Claude-Opus-4.6-High-Reasoning")
prompt = tokenizer.apply_chat_template(messages, tokenize=False)

# Generate
outputs = llm.generate(prompt, sampling_params)

# Print output
for output in outputs:
    print(output.outputs[0].text)

Online Inference (Streaming)

python

from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

llm = LLM(
    model="HarleyWang/Qwen3.5-27B-Claude-Opus-4.6-High-Reasoning",
    dtype="bfloat16",
    tensor_parallel_size=2,
)

tokenizer = AutoTokenizer.from_pretrained("HarleyWang/Qwen3.5-27B-Claude-Opus-4.6-High-Reasoning")

messages = [
    {"role": "user", "content": "Write a Python function to sort a list."}
]
prompt = tokenizer.apply_chat_template(messages, tokenize=False)

sampling_params = SamplingParams(
    temperature=0.7,
    top_p=0.9,
    max_tokens=1024,
    stream=True,  # Enable streaming
)

for output in llm.generate(prompt, sampling_params, use_tqdm=False):
    print(output.outputs[0].text, end="", flush=True)
print()

Offline Inference (Batch)

python

from vllm import LLM, SamplingParams

llm = LLM(
    model="HarleyWang/Qwen3.5-27B-Claude-Opus-4.6-High-Reasoning",
    dtype="bfloat16",
    tensor_parallel_size=2,
)

prompts = [
    "Explain quantum computing.",
    "Write a haiku about coding.",
    "Debug: Why is this loop infinite?",
]

sampling_params = SamplingParams(
    temperature=0.7,
    top_p=0.9,
    max_tokens=512,
)

outputs = llm.generate(prompts, sampling_params)

for output in outputs:
    print(f"Prompt: {output.prompt}")
    print(f"Response: {output.outputs[0].text}")
    print("-" * 50)

Command Line Interface

bash

# Start an OpenAI-compatible API server
python -m vllm.entrypoints.openai.api_server \
    --model HarleyWang/Qwen3.5-27B-Claude-Opus-4.6-High-Reasoning \
    --dtype bfloat16 \
    --tensor-parallel-size 2 \
    --host 0.0.0.0 \
    --port 8000

# In another terminal, use the API
curl http://localhost:8000/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
        "model": "default",
        "messages": [
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": "What is the capital of France?"}
        ],
        "temperature": 0.7,
        "max_tokens": 256
    }'

License

This model is licensed under Apache-2.0.

This model was distilled to capture Claude Opus 4.6's reasoning capabilities while maintaining Qwen3.5-27B's efficiency and multilingual support. Recommended for inference with vLLM for optimal performance.