Skip to content
Local AI Wizard
Your machine
Theme

Qwen3-VL-30B-A3B-Instruct

Alibaba · Qwen/Qwen3-VL-30B-A3B-Instruct

Weights license: Apache 2.0 · code and components may use other terms

Hub downloads · 30 days319.6KPopularity, not quality · read 2026-10-25
Memory needed~24 GBQ4 weights + working room, before the machine's reserve
Parameters31.1 BHub safetensors total
Repository updated2025-11-26A commit is not a release date

Quality

No comparable score

We track no public, comparable benchmark that covers this model yet. No score is inferred.

Reported by the publisher

The publisher's card states no benchmark result for this checkpoint (read 2026-10-25). not published on the card · read 2026-10-25

Runs on

Fast memory holds it 42

The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.

Show all 42

Within memory, outside the fast part 51

Within the machine's memory, outside its fast part: on a graphics card the layers that do not fit run on the CPU from PC RAM (the listed RAM, or 32 GB assumed); on a Mac, above the macOS default GPU share. Not a speed figure.

Show all 51

One memory tier short 9

The same machines with the next memory size up would hold it in fast memory.

Show all 9

Hardware profiles grouped by the Q4 planning estimate on each machine (dedicated GPUs reserve 2 GB; unified and system memory 25%, 2 to 8 GB): the fast memory holds it, it is within memory but outside the fast part (layers offloaded to PC RAM, or above the macOS GPU share), or the machine is one memory tier short. Not a measured fit or speed.

Consider it for

Alibaba released Qwen3-VL-30B-A3B-Instruct on 2025-10-04: a vision-language model that answers about images, with 31.1B parameters on the Hugging Face count and the Apache 2.0 license.

Check first

License: commercial use allowed. At Q4 the weights load about 23.3 GB before each machine's reserve; image resolution, video frames and context add memory, and the vision encoder needs support in the runtime you pick.

Measured speed

No published measurement for this checkpoint

Tokens per second are shown only when a source publishes them with hardware, build and setup. They are never estimated.

How to run

Runtime compatibility and tokens per second have not been measured for this entry. Published metadata and a memory estimate do not prove a successful local run.

Library in source: transformers

Documented ways to run it

Copied as printed in the linked source (read 2026-10-18); not run by this site.

Setup stated first by the source · Transformers
pip install git+https://github.com/huggingface/transformers
# pip install transformers==4.57.0 # currently, V4.57.0 is not released
Transformers · model card · Using 🤗 Transformers to Chat
from transformers import Qwen3VLMoeForConditionalGeneration, AutoProcessor

# default: Load the model on the available device(s)
model = Qwen3VLMoeForConditionalGeneration.from_pretrained(
    "Qwen/Qwen3-VL-30B-A3B-Instruct", dtype="auto", device_map="auto"
)

# We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
# model = Qwen3VLMoeForConditionalGeneration.from_pretrained(
#     "Qwen/Qwen3-VL-30B-A3B-Instruct",
#     dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

processor = AutoProcessor.from_pretrained("Qwen/Qwen3-VL-30B-A3B-Instruct")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Describe this image."},
        ],
    }
]

# Preparation for inference
inputs = processor.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    return_tensors="pt"
)

# Inference: Generation of the output
generated_ids = model.generate(**inputs, max_new_tokens=128)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)

Choose my computer

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Task
image-text-to-text
Architecture
Qwen3VLMoeForConditionalGeneration
Library in source
transformers
Weight license
Apache 2.0Qwen/Qwen3-VL-30B-A3B-Instruct model card (Hugging Face) · read 2026-10-18source
Commercial use
Allowed Apache License 2.0 text (SPDX) · read 2026-10-18license text
Released
Qwen3-VL README news (GitHub) · read 2026-10-18source
Every stored field12 fields
Revision checked
9c4b90e1e4ba969fd3b5378b57d966d725f1b86c
Architecture
Qwen3VLMoeForConditionalGeneration
Library
transformers
Hub task tag
image-text-to-text
Formats
transformers, safetensors
Access
Open download
Publisher kind
Official
Hub parameter count
31,070,754,032safetensors.total
Repository created
2025-09-30creation is not the model's release
Repository updated
2025-11-26a commit is not a release date
Hub downloads (30 days) · likes
319,565 · 623this repository only · read 2026-10-25
Catalog state
Hub config or weights found; no inventory benchmark link

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Curated facts checked: 2026-10-18. The license and release date cite the publisher's sources; parameters, files and task come from the Hugging Face record, and memory is a labelled estimate from its parameter count. A value no source states stays empty; a repository commit is not a model release date.