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

Libraries

How to use unsloth/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="unsloth/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("unsloth/Qwen3.6-35B-A3B-NVFP4")
model = AutoModelForMultimodalLM.from_pretrained("unsloth/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 unsloth/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 "unsloth/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": "unsloth/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/unsloth/Qwen3.6-35B-A3B-NVFP4

SGLang

How to use unsloth/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 "unsloth/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": "unsloth/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 "unsloth/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": "unsloth/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"
						}
					}
				]
			}
		]
	}'

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

ValueError: moe_backend='flashinfer_b12x' is not supported for FP8 MoE.

by shakhizat - opened Jul 13

Discussion

shakhizat

Jul 13

Hello,

When running on an NVIDIA RTX PRO 6000 Blackwell GPU, I encountered the following issue:

ValueError: moe_backend='flashinfer_b12x' is not supported for FP8 MoE. Expected one of ['triton', 'deep_gemm', 'cutlass', 'flashinfer_trtllm', 'flashinfer_cutlass', 'marlin', 'humming', 'aiter', 'hpc'].
[rank0]:[W713 13:28:01.345067028 ProcessGroupNCCL.cpp:1575] Warning: WARNING: destroy_process_group() was not called before program exit, which can leak resources. For more info, please see https://pytorch.org/docs/stable/distributed.html#shutdown (function operator())

moranilt

Jul 14

on dgx spark the same error

danielhanchen

Unsloth AI org Jul 15

@shakhizat For RTX PRO 6000 - no need for the flag - set "flashinfer_trtllm" or "flashinfer_cutlass"

@moranilt You need the latest vLLM:

uv venv unsloth-nvfp4-env --python 3.13
source unsloth-nvfp4-env/bin/activate
uv pip install "vllm>=0.25.0" "flashinfer-python>=0.6.13" "nvidia-cutlass-dsl>=4.5.2" \
    --torch-backend=auto

export CUTE_DSL_ARCH=sm_121a
vllm serve unsloth/Qwen3.6-35B-A3B-NVFP4 --moe-backend flashinfer_b12x

moranilt

Jul 15

@danielhanchen tell me what should I add for this docker compose setup. I'm using ifficial vllm image v0.25.0

  qwen-dense:
    image: vllm/vllm-openai:v0.25.0
    container_name: qwen-dense
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids: ['0'] 
              capabilities: [gpu]
    environment:
      - HF_TOKEN=token
      - CUTE_DSL_ARCH=sm_121a
      - CUDA_VISIBLE_DEVICES=0
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface
    ipc: host
    ports:
      - "8000:8000"
    command: >
      --model unsloth/Qwen3.6-27B-NVFP4
      --port 8000
      --reasoning-parser qwen3
      --dtype auto
      --kv-cache-dtype fp8
      --tensor-parallel-size 1
      --max-num-seqs 8
      --max-model-len 190000
      --gpu-memory-utilization 0.7
      --trust-remote-code
      --enable-prefix-caching
      --enable-prompt-tokens-details
      --max-num-batched-tokens 65536
      --enable-auto-tool-choice
      --tool-call-parser qwen3_coder
      --quantization compressed-tensors
      --attention-backend flashinfer
      --moe-backend flashinfer_b12x
      --enable-chunked-prefill
      --async-scheduling
      --speculative-config '{"method":"mtp","num_speculative_tokens":2}'
      --default-chat-template-kwargs '{"preserve_thinking":false}'

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