Instructions to use ig1/Qwen3.6-35B-A3B-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ig1/Qwen3.6-35B-A3B-NVFP4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="ig1/Qwen3.6-35B-A3B-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("ig1/Qwen3.6-35B-A3B-NVFP4")
model = AutoModelForMultimodalLM.from_pretrained("ig1/Qwen3.6-35B-A3B-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 ig1/Qwen3.6-35B-A3B-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ig1/Qwen3.6-35B-A3B-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": "ig1/Qwen3.6-35B-A3B-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/ig1/Qwen3.6-35B-A3B-NVFP4

SGLang

How to use ig1/Qwen3.6-35B-A3B-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 "ig1/Qwen3.6-35B-A3B-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": "ig1/Qwen3.6-35B-A3B-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 "ig1/Qwen3.6-35B-A3B-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": "ig1/Qwen3.6-35B-A3B-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 ig1/Qwen3.6-35B-A3B-NVFP4 with Docker Model Runner:
```
docker model run hf.co/ig1/Qwen3.6-35B-A3B-NVFP4
```

hekmon commited on May 21

Commit

b778364

verified ·

1 Parent(s): f538d0d

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -200,7 +200,7 @@ docker run --rm --name 'Qwen3.6-35B-A3B-NVFP4' \
 | `--max-num-seqs` | `≤32` | Limit concurrent sequences, can not be higher than max-cudagraph-capture-size | Included above |
 | `--max-num-batched-tokens` | `2048` | Reduce activation buffers | Saves ~350 MiB |
-About the `--speculative-config '{"method": "mtp", "num_speculative_tokens": 1}'`: this will speed up generation in a low concurrent users/requests scenario but the MTP layers eat ~800M of your VRAM decreasing the space available for the KV cache (equivalent to roughly ~26,400 tokens). Because the purpose here was to save VRAM we did not include it. But in the end, it is up to you to decide if you prefer faster inference with a lower KV cache and slower inference with a bigger KV cache.
 #### Windows with Docker for WSL

 | `--max-num-seqs` | `≤32` | Limit concurrent sequences, can not be higher than max-cudagraph-capture-size | Included above |
 | `--max-num-batched-tokens` | `2048` | Reduce activation buffers | Saves ~350 MiB |
+About the `--speculative-config '{"method": "mtp", "num_speculative_tokens": 1}'`: this will speed up generation in a low concurrent users/requests scenario but the MTP layers eat ~1.69G of your VRAM decreasing the space available for the KV cache (equivalent to roughly ~26,400 tokens). Because the purpose here was to save VRAM we did not include it. But in the end, it is up to you to decide if you prefer faster inference with a lower KV cache and slower inference with a bigger KV cache.
 #### Windows with Docker for WSL