Skip to content
Local AI Wizard
Your machine
Theme

Recon2Reason-Reasoning-4B

BAAI · BAAI/Recon2Reason-Reasoning-4B

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

Hub downloads · 30 days352Popularity, not quality · read 2026-10-25
Memory needed~4 GBQ4 weights + working room, before the machine's reserve
Parameters4.4 BHub safetensors total
Repository updated2026-09-03A 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 118

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

Show all 118

Within memory, outside the fast part 1

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.

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

Recon2Reason-Reasoning-4B by BAAI (the publisher states no release date): a vision-language model that answers about images, with 4.4B parameters on the Hugging Face count and the Apache 2.0 license. Languages the publisher declares: en.

Check first

License: commercial use allowed. At Q4 the weights load about 3.3 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 "transformers==4.57.1" "torch>=2.6" accelerate safetensors pillow
Transformers · model card · Quick start
import torch
from transformers import AutoProcessor, Qwen3VLForConditionalGeneration

model_id = "BAAI/Recon2Reason-Reasoning-4B"

processor = AutoProcessor.from_pretrained(model_id)
model = Qwen3VLForConditionalGeneration.from_pretrained(
    model_id,
    dtype="auto",
    device_map="auto",
).eval()

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": "path/to/scene.jpg"},
            {
                "type": "text",
                "text": "Which object is closest to the chair? ",
            },
        ],
    }
]

inputs = processor.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device)

with torch.inference_mode():
    output_ids = model.generate(
        **inputs,
        max_new_tokens=512,
        do_sample=False,
    )

generated_ids = output_ids[:, inputs["input_ids"].shape[1]:]
answer = processor.batch_decode(
    generated_ids,
    skip_special_tokens=True,
    clean_up_tokenization_spaces=False,
)[0]
print(answer)

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
Qwen3VLForConditionalGeneration
Library in source
transformers
Weight license
Apache 2.0BAAI/Recon2Reason-Reasoning-4B model card (Hugging Face) · read 2026-10-18source
Commercial use
Allowed Apache License 2.0 text (SPDX) · read 2026-10-18license text
Languages
enModel card metadata · read 2026-10-25source
Released
Not published by the publisher. Model card read in full: it states no release date and links no paper or announcement; the Hugging Face papers index has no Recon2Reason paper. No date is inferred from the repository.Checked 2026-10-18.source checked
Every stored field12 fields
Revision checked
f8faf41a1d5fe392f2d1ee31884f79398da59c99
Architecture
Qwen3VLForConditionalGeneration
Library
transformers
Hub task tag
image-text-to-text
Declared base models
Qwen/Qwen3-VL-4B-Instruct
Formats
transformers, safetensors
Access
Open download
Publisher kind
Official
Repository created
2026-09-03creation is not the model's release
Repository updated
2026-09-03a commit is not a release date
Hub downloads (30 days) · likes
352 · 0this 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.