Instructions to use mconcat/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mconcat/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-NVFP4 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="mconcat/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-NVFP4")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("mconcat/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-NVFP4")
model = AutoModelForMultimodalLM.from_pretrained("mconcat/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-NVFP4", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mconcat/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mconcat/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mconcat/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mconcat/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-NVFP4

SGLang

How to use mconcat/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-NVFP4 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "mconcat/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-NVFP4" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mconcat/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "mconcat/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-NVFP4" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mconcat/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mconcat/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-NVFP4 with Docker Model Runner:
```
docker model run hf.co/mconcat/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-NVFP4
```

AWQ 4-bit version of this Opus-Distilled-v2 model?

by celikburak - opened Mar 29

Discussion

celikburak

Mar 29

Hi,
Thank you for your excellent NVFP4 quantizations.
I'm using Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2 (the v2 version with 14k Opus samples). It's currently the best reasoning model I have for coding and agent tasks - shorter CoT, better efficiency than base Qwen3.5-27B.

However, I'm on a single RTX 5090 and really want to run it with vLLM + FlashInfer to get MTP, continuous batching and higher speed.
Would you consider making an AWQ 4-bit version of this Opus-Distilled-v2 model?
The distillation dataset is public, so the data is already available. Many users with 40/50-series cards are waiting for a good AWQ quant of this specific model.
Thanks in advance!

Best regards

mconcat

Owner Mar 30

omw

mconcat

Owner Mar 31

https://huggingface.co/mconcat/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-AWQ-4bit

Let me know if there are any errors or problems

celikburak

Mar 31

https://huggingface.co/mconcat/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-AWQ-4bit

Let me know if there are any errors or problems

Huge thanks for the lightning-fast!
Just 1 day after the request.
Now I can finally run this beast with vLLM + FlashInfer → MTP + continuous batching. Going from ~45 tok/s (GGUF) to potentially 150+ tok/s on a single 5090.
This is why open source is unbeatable. 🙏🔥

I'll provide feedback right away if I run into any issues.
Do you have any suggestions or tips before I start testing it with vLLM + FlashInfer?

ELVISIO

Apr 1

https://huggingface.co/mconcat/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-AWQ-4bit

Let me know if there are any errors or problems

@mconcat Thank you for your sharing!!! Would you consider making an 4B/9B AWQ 4bit model? Many Thanks!! I can run it on my laptop, lol

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment