Instructions to use Sehyo/Qwen3.5-122B-A10B-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sehyo/Qwen3.5-122B-A10B-NVFP4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="Sehyo/Qwen3.5-122B-A10B-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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Sehyo/Qwen3.5-122B-A10B-NVFP4")
model = AutoModelForMultimodalLM.from_pretrained("Sehyo/Qwen3.5-122B-A10B-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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Sehyo/Qwen3.5-122B-A10B-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Sehyo/Qwen3.5-122B-A10B-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": "Sehyo/Qwen3.5-122B-A10B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Sehyo/Qwen3.5-122B-A10B-NVFP4

SGLang

How to use Sehyo/Qwen3.5-122B-A10B-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 "Sehyo/Qwen3.5-122B-A10B-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": "Sehyo/Qwen3.5-122B-A10B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "Sehyo/Qwen3.5-122B-A10B-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": "Sehyo/Qwen3.5-122B-A10B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use Sehyo/Qwen3.5-122B-A10B-NVFP4 with Docker Model Runner:
```
docker model run hf.co/Sehyo/Qwen3.5-122B-A10B-NVFP4
```

1M context

by mtcl - opened Feb 26

Discussion

mtcl

Feb 26

How do I get to 1M context out of this?

hellofans

Feb 27

you do not, this quant is calibrated only for 4096 tokens

mtcl

Feb 27

So what does that mean? Can I only use it for 4096 tokens?

Sehyo

Owner Feb 28

No that is not what that means, you can use it with the supported context length for Qwen 3.5. 4096 is more than plenty for calibration.

ichiro-maruta

Mar 4

To add to what @Sehyo mentioned: the model's architecture indeed supports the full context, and 4096 is perfectly fine for calibration.

However, there is a known artifact with quantization tools (like llm-compressor). They often accidentally hardcode the calibration length into the final tokenizer.json as a permanent truncation rule:

  "truncation": {
    "direction": "Right",
    "max_length": 4096,
    "strategy": "LongestFirst",
    "stride": 0
  }

Because of this, frameworks like vLLM silently truncate any input over 4096 tokens. In my case, this caused a complete crash (ValueError: Mismatch in 'image' token count) when processing high-res images.

How I resolved it:
In my environment, I was able to fix this issue and successfully unlock the full context by modifying the downloaded tokenizer.json locally to:

  "truncation": null

@Sehyo :
Could you please update the tokenizer.json in this repository to "truncation": null? This quick fix will prevent silent truncations for everyone. Thanks for the amazing model!

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