Instructions to use Qwen/Qwen3-VL-32B-Instruct-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Qwen/Qwen3-VL-32B-Instruct-FP8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="Qwen/Qwen3-VL-32B-Instruct-FP8") 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, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("Qwen/Qwen3-VL-32B-Instruct-FP8") model = AutoModelForImageTextToText.from_pretrained("Qwen/Qwen3-VL-32B-Instruct-FP8") 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
- vLLM
How to use Qwen/Qwen3-VL-32B-Instruct-FP8 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Qwen/Qwen3-VL-32B-Instruct-FP8" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Qwen/Qwen3-VL-32B-Instruct-FP8", "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/Qwen/Qwen3-VL-32B-Instruct-FP8
- SGLang
How to use Qwen/Qwen3-VL-32B-Instruct-FP8 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 "Qwen/Qwen3-VL-32B-Instruct-FP8" \ --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": "Qwen/Qwen3-VL-32B-Instruct-FP8", "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 "Qwen/Qwen3-VL-32B-Instruct-FP8" \ --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": "Qwen/Qwen3-VL-32B-Instruct-FP8", "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 Qwen/Qwen3-VL-32B-Instruct-FP8 with Docker Model Runner:
docker model run hf.co/Qwen/Qwen3-VL-32B-Instruct-FP8
| { | |
| "architectures": [ | |
| "Qwen3VLForConditionalGeneration" | |
| ], | |
| "image_token_id": 151655, | |
| "model_type": "qwen3_vl", | |
| "text_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 151645, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 25600, | |
| "max_position_embeddings": 262144, | |
| "model_type": "qwen3_vl_text", | |
| "num_attention_heads": 64, | |
| "num_hidden_layers": 64, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "mrope_interleaved": true, | |
| "mrope_section": [ | |
| 24, | |
| 20, | |
| 20 | |
| ], | |
| "rope_type": "default" | |
| }, | |
| "rope_theta": 5000000, | |
| "use_cache": true, | |
| "vocab_size": 151936 | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "4.57.0.dev0", | |
| "video_token_id": 151656, | |
| "vision_config": { | |
| "deepstack_visual_indexes": [ | |
| 8, | |
| 16, | |
| 24 | |
| ], | |
| "depth": 27, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "in_channels": 3, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4304, | |
| "model_type": "qwen3_vl", | |
| "num_heads": 16, | |
| "num_position_embeddings": 2304, | |
| "out_hidden_size": 5120, | |
| "patch_size": 16, | |
| "spatial_merge_size": 2, | |
| "temporal_patch_size": 2 | |
| }, | |
| "vision_end_token_id": 151653, | |
| "vision_start_token_id": 151652, | |
| "quantization_config": { | |
| "activation_scheme": "dynamic", | |
| "fmt": "e4m3", | |
| "quant_method": "fp8", | |
| "ignored_layers": [ | |
| "lm_head", | |
| "model.visual.merger.linear_fc1", | |
| "model.visual.merger.linear_fc2", | |
| "model.visual.merger.norm", | |
| "model.visual.patch_embed.proj", | |
| "model.visual.pos_embed", | |
| "visual.merger.linear_fc1", | |
| "visual.merger.linear_fc2", | |
| "visual.merger.norm", | |
| "visual.patch_embed.proj", | |
| "visual.pos_embed", | |
| "model.visual.blocks.0.attn.proj", | |
| "model.visual.blocks.0.attn.qkv", | |
| "model.visual.blocks.0.mlp.linear_fc1", | |
| "model.visual.blocks.0.mlp.linear_fc2", | |
| "visual.blocks.0.attn.proj", | |
| "visual.blocks.0.attn.qkv_proj", | |
| "visual.blocks.0.mlp.linear_fc1", | |
| "visual.blocks.0.mlp.linear_fc2", | |
| "model.visual.blocks.1.attn.proj", | |
| "model.visual.blocks.1.attn.qkv", | |
| "model.visual.blocks.1.mlp.linear_fc1", | |
| "model.visual.blocks.1.mlp.linear_fc2", | |
| "visual.blocks.1.attn.proj", | |
| "visual.blocks.1.attn.qkv_proj", | |
| "visual.blocks.1.mlp.linear_fc1", | |
| "visual.blocks.1.mlp.linear_fc2", | |
| "model.visual.blocks.2.attn.proj", | |
| "model.visual.blocks.2.attn.qkv", | |
| "model.visual.blocks.2.mlp.linear_fc1", | |
| "model.visual.blocks.2.mlp.linear_fc2", | |
| "visual.blocks.2.attn.proj", | |
| "visual.blocks.2.attn.qkv_proj", | |
| "visual.blocks.2.mlp.linear_fc1", | |
| "visual.blocks.2.mlp.linear_fc2", | |
| "model.visual.blocks.3.attn.proj", | |
| "model.visual.blocks.3.attn.qkv", | |
| "model.visual.blocks.3.mlp.linear_fc1", | |
| "model.visual.blocks.3.mlp.linear_fc2", | |
| "visual.blocks.3.attn.proj", | |
| "visual.blocks.3.attn.qkv_proj", | |
| "visual.blocks.3.mlp.linear_fc1", | |
| "visual.blocks.3.mlp.linear_fc2", | |
| "model.visual.blocks.4.attn.proj", | |
| "model.visual.blocks.4.attn.qkv", | |
| "model.visual.blocks.4.mlp.linear_fc1", | |
| "model.visual.blocks.4.mlp.linear_fc2", | |
| "visual.blocks.4.attn.proj", | |
| "visual.blocks.4.attn.qkv_proj", | |
| "visual.blocks.4.mlp.linear_fc1", | |
| "visual.blocks.4.mlp.linear_fc2", | |
| "model.visual.blocks.5.attn.proj", | |
| "model.visual.blocks.5.attn.qkv", | |
| "model.visual.blocks.5.mlp.linear_fc1", | |
| "model.visual.blocks.5.mlp.linear_fc2", | |
| "visual.blocks.5.attn.proj", | |
| "visual.blocks.5.attn.qkv_proj", | |
| "visual.blocks.5.mlp.linear_fc1", | |
| "visual.blocks.5.mlp.linear_fc2", | |
| "model.visual.blocks.6.attn.proj", | |
| "model.visual.blocks.6.attn.qkv", | |
| "model.visual.blocks.6.mlp.linear_fc1", | |
| "model.visual.blocks.6.mlp.linear_fc2", | |
| "visual.blocks.6.attn.proj", | |
| "visual.blocks.6.attn.qkv_proj", | |
| "visual.blocks.6.mlp.linear_fc1", | |
| "visual.blocks.6.mlp.linear_fc2", | |
| "model.visual.blocks.7.attn.proj", | |
| "model.visual.blocks.7.attn.qkv", | |
| "model.visual.blocks.7.mlp.linear_fc1", | |
| "model.visual.blocks.7.mlp.linear_fc2", | |
| "visual.blocks.7.attn.proj", | |
| "visual.blocks.7.attn.qkv_proj", | |
| "visual.blocks.7.mlp.linear_fc1", | |
| "visual.blocks.7.mlp.linear_fc2", | |
| "model.visual.blocks.8.attn.proj", | |
| "model.visual.blocks.8.attn.qkv", | |
| "model.visual.blocks.8.mlp.linear_fc1", | |
| "model.visual.blocks.8.mlp.linear_fc2", | |
| "visual.blocks.8.attn.proj", | |
| "visual.blocks.8.attn.qkv_proj", | |
| "visual.blocks.8.mlp.linear_fc1", | |
| "visual.blocks.8.mlp.linear_fc2", | |
| "model.visual.blocks.9.attn.proj", | |
| "model.visual.blocks.9.attn.qkv", | |
| "model.visual.blocks.9.mlp.linear_fc1", | |
| "model.visual.blocks.9.mlp.linear_fc2", | |
| "visual.blocks.9.attn.proj", | |
| "visual.blocks.9.attn.qkv_proj", | |
| "visual.blocks.9.mlp.linear_fc1", | |
| "visual.blocks.9.mlp.linear_fc2", | |
| "model.visual.blocks.10.attn.proj", | |
| "model.visual.blocks.10.attn.qkv", | |
| "model.visual.blocks.10.mlp.linear_fc1", | |
| "model.visual.blocks.10.mlp.linear_fc2", | |
| "visual.blocks.10.attn.proj", | |
| "visual.blocks.10.attn.qkv_proj", | |
| "visual.blocks.10.mlp.linear_fc1", | |
| "visual.blocks.10.mlp.linear_fc2", | |
| "model.visual.blocks.11.attn.proj", | |
| "model.visual.blocks.11.attn.qkv", | |
| "model.visual.blocks.11.mlp.linear_fc1", | |
| "model.visual.blocks.11.mlp.linear_fc2", | |
| "visual.blocks.11.attn.proj", | |
| "visual.blocks.11.attn.qkv_proj", | |
| "visual.blocks.11.mlp.linear_fc1", | |
| "visual.blocks.11.mlp.linear_fc2", | |
| "model.visual.blocks.12.attn.proj", | |
| "model.visual.blocks.12.attn.qkv", | |
| "model.visual.blocks.12.mlp.linear_fc1", | |
| "model.visual.blocks.12.mlp.linear_fc2", | |
| "visual.blocks.12.attn.proj", | |
| "visual.blocks.12.attn.qkv_proj", | |
| "visual.blocks.12.mlp.linear_fc1", | |
| "visual.blocks.12.mlp.linear_fc2", | |
| "model.visual.blocks.13.attn.proj", | |
| "model.visual.blocks.13.attn.qkv", | |
| "model.visual.blocks.13.mlp.linear_fc1", | |
| "model.visual.blocks.13.mlp.linear_fc2", | |
| "visual.blocks.13.attn.proj", | |
| "visual.blocks.13.attn.qkv_proj", | |
| "visual.blocks.13.mlp.linear_fc1", | |
| "visual.blocks.13.mlp.linear_fc2", | |
| "model.visual.blocks.14.attn.proj", | |
| "model.visual.blocks.14.attn.qkv", | |
| "model.visual.blocks.14.mlp.linear_fc1", | |
| "model.visual.blocks.14.mlp.linear_fc2", | |
| "visual.blocks.14.attn.proj", | |
| "visual.blocks.14.attn.qkv_proj", | |
| "visual.blocks.14.mlp.linear_fc1", | |
| "visual.blocks.14.mlp.linear_fc2", | |
| "model.visual.blocks.15.attn.proj", | |
| "model.visual.blocks.15.attn.qkv", | |
| "model.visual.blocks.15.mlp.linear_fc1", | |
| "model.visual.blocks.15.mlp.linear_fc2", | |
| "visual.blocks.15.attn.proj", | |
| "visual.blocks.15.attn.qkv_proj", | |
| "visual.blocks.15.mlp.linear_fc1", | |
| "visual.blocks.15.mlp.linear_fc2", | |
| "model.visual.blocks.16.attn.proj", | |
| "model.visual.blocks.16.attn.qkv", | |
| "model.visual.blocks.16.mlp.linear_fc1", | |
| "model.visual.blocks.16.mlp.linear_fc2", | |
| "visual.blocks.16.attn.proj", | |
| "visual.blocks.16.attn.qkv_proj", | |
| "visual.blocks.16.mlp.linear_fc1", | |
| "visual.blocks.16.mlp.linear_fc2", | |
| "model.visual.blocks.17.attn.proj", | |
| "model.visual.blocks.17.attn.qkv", | |
| "model.visual.blocks.17.mlp.linear_fc1", | |
| "model.visual.blocks.17.mlp.linear_fc2", | |
| "visual.blocks.17.attn.proj", | |
| "visual.blocks.17.attn.qkv_proj", | |
| "visual.blocks.17.mlp.linear_fc1", | |
| "visual.blocks.17.mlp.linear_fc2", | |
| "model.visual.blocks.18.attn.proj", | |
| "model.visual.blocks.18.attn.qkv", | |
| "model.visual.blocks.18.mlp.linear_fc1", | |
| "model.visual.blocks.18.mlp.linear_fc2", | |
| "visual.blocks.18.attn.proj", | |
| "visual.blocks.18.attn.qkv_proj", | |
| "visual.blocks.18.mlp.linear_fc1", | |
| "visual.blocks.18.mlp.linear_fc2", | |
| "model.visual.blocks.19.attn.proj", | |
| "model.visual.blocks.19.attn.qkv", | |
| "model.visual.blocks.19.mlp.linear_fc1", | |
| "model.visual.blocks.19.mlp.linear_fc2", | |
| "visual.blocks.19.attn.proj", | |
| "visual.blocks.19.attn.qkv_proj", | |
| "visual.blocks.19.mlp.linear_fc1", | |
| "visual.blocks.19.mlp.linear_fc2", | |
| "model.visual.blocks.20.attn.proj", | |
| "model.visual.blocks.20.attn.qkv", | |
| "model.visual.blocks.20.mlp.linear_fc1", | |
| "model.visual.blocks.20.mlp.linear_fc2", | |
| "visual.blocks.20.attn.proj", | |
| "visual.blocks.20.attn.qkv_proj", | |
| "visual.blocks.20.mlp.linear_fc1", | |
| "visual.blocks.20.mlp.linear_fc2", | |
| "model.visual.blocks.21.attn.proj", | |
| "model.visual.blocks.21.attn.qkv", | |
| "model.visual.blocks.21.mlp.linear_fc1", | |
| "model.visual.blocks.21.mlp.linear_fc2", | |
| "visual.blocks.21.attn.proj", | |
| "visual.blocks.21.attn.qkv_proj", | |
| "visual.blocks.21.mlp.linear_fc1", | |
| "visual.blocks.21.mlp.linear_fc2", | |
| "model.visual.blocks.22.attn.proj", | |
| "model.visual.blocks.22.attn.qkv", | |
| "model.visual.blocks.22.mlp.linear_fc1", | |
| "model.visual.blocks.22.mlp.linear_fc2", | |
| "visual.blocks.22.attn.proj", | |
| "visual.blocks.22.attn.qkv_proj", | |
| "visual.blocks.22.mlp.linear_fc1", | |
| "visual.blocks.22.mlp.linear_fc2", | |
| "model.visual.blocks.23.attn.proj", | |
| "model.visual.blocks.23.attn.qkv", | |
| "model.visual.blocks.23.mlp.linear_fc1", | |
| "model.visual.blocks.23.mlp.linear_fc2", | |
| "visual.blocks.23.attn.proj", | |
| "visual.blocks.23.attn.qkv_proj", | |
| "visual.blocks.23.mlp.linear_fc1", | |
| "visual.blocks.23.mlp.linear_fc2", | |
| "model.visual.blocks.24.attn.proj", | |
| "model.visual.blocks.24.attn.qkv", | |
| "model.visual.blocks.24.mlp.linear_fc1", | |
| "model.visual.blocks.24.mlp.linear_fc2", | |
| "visual.blocks.24.attn.proj", | |
| "visual.blocks.24.attn.qkv_proj", | |
| "visual.blocks.24.mlp.linear_fc1", | |
| "visual.blocks.24.mlp.linear_fc2", | |
| "model.visual.blocks.25.attn.proj", | |
| "model.visual.blocks.25.attn.qkv", | |
| "model.visual.blocks.25.mlp.linear_fc1", | |
| "model.visual.blocks.25.mlp.linear_fc2", | |
| "visual.blocks.25.attn.proj", | |
| "visual.blocks.25.attn.qkv_proj", | |
| "visual.blocks.25.mlp.linear_fc1", | |
| "visual.blocks.25.mlp.linear_fc2", | |
| "model.visual.blocks.26.attn.proj", | |
| "model.visual.blocks.26.attn.qkv", | |
| "model.visual.blocks.26.mlp.linear_fc1", | |
| "model.visual.blocks.26.mlp.linear_fc2", | |
| "visual.blocks.26.attn.proj", | |
| "visual.blocks.26.attn.qkv_proj", | |
| "visual.blocks.26.mlp.linear_fc1", | |
| "visual.blocks.26.mlp.linear_fc2", | |
| "model.visual.deepstack_merger_list.0.linear_fc1", | |
| "model.visual.deepstack_merger_list.0.linear_fc2", | |
| "model.visual.deepstack_merger_list.0.norm", | |
| "visual.deepstack_merger_list.0.linear_fc1", | |
| "visual.deepstack_merger_list.0.linear_fc2", | |
| "visual.deepstack_merger_list.0.norm", | |
| "model.visual.deepstack_merger_list.1.linear_fc1", | |
| "model.visual.deepstack_merger_list.1.linear_fc2", | |
| "model.visual.deepstack_merger_list.1.norm", | |
| "visual.deepstack_merger_list.1.linear_fc1", | |
| "visual.deepstack_merger_list.1.linear_fc2", | |
| "visual.deepstack_merger_list.1.norm", | |
| "model.visual.deepstack_merger_list.2.linear_fc1", | |
| "model.visual.deepstack_merger_list.2.linear_fc2", | |
| "model.visual.deepstack_merger_list.2.norm", | |
| "visual.deepstack_merger_list.2.linear_fc1", | |
| "visual.deepstack_merger_list.2.linear_fc2", | |
| "visual.deepstack_merger_list.2.norm" | |
| ], | |
| "weight_block_size": [ | |
| 128, | |
| 128 | |
| ] | |
| } | |
| } |