Instructions to use unsloth/Qwen2.5-VL-32B-Instruct-unsloth-bnb-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/Qwen2.5-VL-32B-Instruct-unsloth-bnb-4bit with Transformers:

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

pipe = pipeline("image-text-to-text", model="unsloth/Qwen2.5-VL-32B-Instruct-unsloth-bnb-4bit")
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/Qwen2.5-VL-32B-Instruct-unsloth-bnb-4bit")
model = AutoModelForMultimodalLM.from_pretrained("unsloth/Qwen2.5-VL-32B-Instruct-unsloth-bnb-4bit", 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/Qwen2.5-VL-32B-Instruct-unsloth-bnb-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/Qwen2.5-VL-32B-Instruct-unsloth-bnb-4bit"
# 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/Qwen2.5-VL-32B-Instruct-unsloth-bnb-4bit",
		"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/Qwen2.5-VL-32B-Instruct-unsloth-bnb-4bit

SGLang

How to use unsloth/Qwen2.5-VL-32B-Instruct-unsloth-bnb-4bit 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/Qwen2.5-VL-32B-Instruct-unsloth-bnb-4bit" \
    --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/Qwen2.5-VL-32B-Instruct-unsloth-bnb-4bit",
		"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/Qwen2.5-VL-32B-Instruct-unsloth-bnb-4bit" \
        --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/Qwen2.5-VL-32B-Instruct-unsloth-bnb-4bit",
		"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/Qwen2.5-VL-32B-Instruct-unsloth-bnb-4bit with Docker Model Runner:
```
docker model run hf.co/unsloth/Qwen2.5-VL-32B-Instruct-unsloth-bnb-4bit
```

Assertion error while loading the model

by b0yan9 - opened Mar 26, 2025

Discussion

b0yan9

Mar 26, 2025

•

edited Mar 26, 2025

Hi,

I tried to use this model but there's an assertion error when loading the model

    assert param_data.shape == loaded_weight.shape
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

My command is vllm serve unsloth/Qwen2.5-VL-32B-Instruct-unsloth-bnb-4bit --dtype bfloat16 --load_format bitsandbytes --quantization bitsandbytes

The full exception output is below

Traceback (most recent call last):
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/engine/multiprocessing/engine.py", line 436, in run_mp_engine
    engine = MQLLMEngine.from_vllm_config(
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/engine/multiprocessing/engine.py", line 128, in from_vllm_config
    return cls(
           ^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/engine/multiprocessing/engine.py", line 82, in __init__
    self.engine = LLMEngine(*args, **kwargs)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/engine/llm_engine.py", line 280, in __init__
    self.model_executor = executor_class(vllm_config=vllm_config, )
                          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/executor/executor_base.py", line 52, in __init__
    self._init_executor()
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/executor/uniproc_executor.py", line 47, in _init_executor
    self.collective_rpc("load_model")
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/executor/uniproc_executor.py", line 56, in collective_rpc
    answer = run_method(self.driver_worker, method, args, kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/utils.py", line 2255, in run_method
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/worker/worker.py", line 183, in load_model
    self.model_runner.load_model()
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/worker/model_runner.py", line 1113, in load_model
    self.model = get_model(vllm_config=self.vllm_config)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/model_executor/model_loader/__init__.py", line 14, in get_model
    return loader.load_model(vllm_config=vllm_config)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/model_executor/model_loader/loader.py", line 1278, in load_model
    self._load_weights(model_config, model)
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/model_executor/model_loader/loader.py", line 1188, in _load_weights
    loaded_weights = model.load_weights(qweight_iterator)
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/model_executor/models/qwen2_5_vl.py", line 1113, in load_weights
    return loader.load_weights(weights, mapper=self.hf_to_vllm_mapper)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/model_executor/models/utils.py", line 235, in load_weights
    autoloaded_weights = set(self._load_module("", self.module, weights))
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/model_executor/models/utils.py", line 196, in _load_module
    yield from self._load_module(prefix,
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/model_executor/models/utils.py", line 173, in _load_module
    loaded_params = module_load_weights(weights)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/model_executor/models/qwen2.py", line 490, in load_weights
    return loader.load_weights(weights)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/model_executor/models/utils.py", line 235, in load_weights
    autoloaded_weights = set(self._load_module("", self.module, weights))
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/model_executor/models/utils.py", line 196, in _load_module
    yield from self._load_module(prefix,
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/model_executor/models/utils.py", line 173, in _load_module
    loaded_params = module_load_weights(weights)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/model_executor/models/qwen2.py", line 403, in load_weights
    weight_loader(param, loaded_weight)
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/model_executor/layers/linear.py", line 1228, in weight_loader
    assert param_data.shape == loaded_weight.shape
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
AssertionError
Process SpawnProcess-1:
Traceback (most recent call last):
  File "/home/bo/.conda/envs/vllm/lib/python3.12/multiprocessing/process.py", line 314, in _bootstrap
    self.run()
  File "/home/bo/.conda/envs/vllm/lib/python3.12/multiprocessing/process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/engine/multiprocessing/engine.py", line 450, in run_mp_engine
    raise e
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/engine/multiprocessing/engine.py", line 436, in run_mp_engine
    engine = MQLLMEngine.from_vllm_config(
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/engine/multiprocessing/engine.py", line 128, in from_vllm_config
    return cls(
           ^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/engine/multiprocessing/engine.py", line 82, in __init__
    self.engine = LLMEngine(*args, **kwargs)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/engine/llm_engine.py", line 280, in __init__
    self.model_executor = executor_class(vllm_config=vllm_config, )
                          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/executor/executor_base.py", line 52, in __init__
    self._init_executor()
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/executor/uniproc_executor.py", line 47, in _init_executor
    self.collective_rpc("load_model")
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/executor/uniproc_executor.py", line 56, in collective_rpc
    answer = run_method(self.driver_worker, method, args, kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/utils.py", line 2255, in run_method
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/worker/worker.py", line 183, in load_model
    self.model_runner.load_model()
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/worker/model_runner.py", line 1113, in load_model
    self.model = get_model(vllm_config=self.vllm_config)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/model_executor/model_loader/__init__.py", line 14, in get_model
    return loader.load_model(vllm_config=vllm_config)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/model_executor/model_loader/loader.py", line 1278, in load_model
    self._load_weights(model_config, model)
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/model_executor/model_loader/loader.py", line 1188, in _load_weights
    loaded_weights = model.load_weights(qweight_iterator)
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/model_executor/models/qwen2_5_vl.py", line 1113, in load_weights
    return loader.load_weights(weights, mapper=self.hf_to_vllm_mapper)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/model_executor/models/utils.py", line 235, in load_weights
    autoloaded_weights = set(self._load_module("", self.module, weights))
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/model_executor/models/utils.py", line 196, in _load_module
    yield from self._load_module(prefix,
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/model_executor/models/utils.py", line 173, in _load_module
    loaded_params = module_load_weights(weights)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/model_executor/models/qwen2.py", line 490, in load_weights
    return loader.load_weights(weights)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/model_executor/models/utils.py", line 235, in load_weights
    autoloaded_weights = set(self._load_module("", self.module, weights))
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/model_executor/models/utils.py", line 196, in _load_module
    yield from self._load_module(prefix,
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/model_executor/models/utils.py", line 173, in _load_module
    loaded_params = module_load_weights(weights)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/model_executor/models/qwen2.py", line 403, in load_weights
    weight_loader(param, loaded_weight)
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/model_executor/layers/linear.py", line 1228, in weight_loader
    assert param_data.shape == loaded_weight.shape
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
AssertionError
Loading safetensors checkpoint shards:  20% Completed | 1/5 [00:01<00:06,  1.59s/it]

Traceback (most recent call last):
  File "/home/bo/.conda/envs/vllm/bin/vllm", line 8, in <module>
    sys.exit(main())
             ^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/entrypoints/cli/main.py", line 75, in main
    args.dispatch_function(args)
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/entrypoints/cli/serve.py", line 33, in cmd
    uvloop.run(run_server(args))
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/uvloop/__init__.py", line 109, in run
    return __asyncio.run(
           ^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/asyncio/runners.py", line 195, in run
    return runner.run(main)
           ^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/asyncio/runners.py", line 118, in run
    return self._loop.run_until_complete(task)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/uvloop/__init__.py", line 61, in wrapper
    return await main
           ^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 1016, in run_server
    async with build_async_engine_client(args) as engine_client:
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/contextlib.py", line 210, in __aenter__
    return await anext(self.gen)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 141, in build_async_engine_client
    async with build_async_engine_client_from_engine_args(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/contextlib.py", line 210, in __aenter__
    return await anext(self.gen)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/bo/.conda/envs/vllm/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 264, in build_async_engine_client_from_engine_args
    raise RuntimeError(
RuntimeError: Engine process failed to start. See stack trace for the root cause.```

Jotakak

Mar 27, 2025

Same issue here. Using the same command to launch Qwen2.5-VL-7B works fine.

lktinhtemp

Mar 27, 2025

same

gyuryeol

Sep 19, 2025

same

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