Open Model Weights
Home / Models / Qwen2.5-VL-3B-Instruct

QWEN · FIELD-VERIFIED

Qwen2.5-VL-3B-Instruct

Checked against the listed Hugging Face source repository on 2026-10-03. Unknown values are left explicit rather than inferred.

Source repository ↗Compare this model →History & diff →Machine-readable JSON ↗Field-verified 2026-10-03
Evidence statusSource-first verified
Repository revision checked2026-10-03
Full field verification2026-10-02
Source policy →Methodology →

MODEL INTELLIGENCE · SOURCE-FIRST

What is Qwen2.5-VL-3B-Instruct?

OMW evidence review3 Oct 2026

Open Model Weights records Qwen2.5-VL-3B-Instruct as a 3.75462B-parameter image + text → text open-weight model in the Qwen2.5-VL family, with Qwen listed as the developer. The checked source repository provides 3 recognized weight artifacts, format evidence for Safetensors and a verified context window of 128,000 tokens. Values that are not evidenced in the checked sources remain explicitly undisclosed or unknown.

The repository declares Qwen Research License. Commercial use requires a separate Qwen license. Open Model Weights reports the checked license evidence and classification; this is not legal advice.

No base model is declared in the checked standard lineage metadata, so Open Model Weights does not infer one. In the checked repository, training or recipe evidence is present.

Source repository ↗Model card ↗Configuration ↗License evidence ↗

DEPLOYMENT PROFILE

Weight memory, without pretending it is a deployment guarantee.

These bars visualize weight-only decimal-GB estimates. They exclude KV cache, activations, runtime overhead, optimizer state and sharding.

WEIGHT-ONLY MEMORY
BF16 / FP16~7.5 GB
FP8 / INT8~3.8 GB
INT4~1.9 GB
FIELD EVIDENCE MAP
WeightsVerified
LicenseVerified
Commercial useClassified
ContextVerified
FormatsVerified
LineageNot declared
Training recipeTraining described in model card
Training dataNot disclosed in checked standard metadata/model card
RuntimeSource-derived · not runtime-tested

LICENSE & USE

Qwen Research License

Commercial use requires a separate Qwen license

Declared licenseQwen Research License
ClassificationSeparate license required
VerificationLicense file checked

This section summarizes the checked repository evidence. It is not legal advice. Inspect license evidence ↗

LINEAGE & PROVENANCE

What the checked sources disclose — and what they do not.

Open Model Weights does not infer a hidden base model or training corpus when the checked sources do not declare one.

LINEAGE
BASE / PARENTBase model not declaredUnknown
not inferred
CURRENT RECORDQwen2.5-VL-3B-InstructQwen2.5-VL
TRAINING DISCLOSURE
Training recipeTraining described in model card
Training dataNot disclosed in checked standard metadata/model card
FamilyQwen2.5-VL

RUNTIME SIGNALS

Compatibility claims stay attached to their evidence level.

Declared and model-card-mentioned runtimes are discovery signals. They are not treated as Open Model Weights runtime tests unless explicitly measured.

DeclaredTransformers
OMW runtime testNot performed

EVIDENCE TRAIL

Sources and observed history.

This is where the article remains auditable: source links on one side, the registry's observed change history on the other.

PrimaryModel Repositoryhttps://huggingface.co/Qwen/Qwen2.5-VL-3B-InstructInspect source ↗PrimaryModel Apihttps://huggingface.co/api/models/Qwen/Qwen2.5-VL-3B-InstructInspect source ↗PrimaryModel Cardhttps://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct/blob/main/README.mdInspect source ↗PrimaryConfighttps://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct/blob/main/config.jsonInspect source ↗Primary Or DeclaredLicensehttps://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct/blob/main/LICENSEInspect source ↗
Repository revision check

Listed Hugging Face source repository SHA unchanged; prior field evidence retained.

Repository revision check

Listed Hugging Face source repository SHA unchanged; prior field evidence retained.

Field-by-field verification

Checked Hugging Face API metadata, exact repository file list, model card and config when accessible.

Registry record created

Previous verification level: discovered-pending.

RELATED RECORDS

Continue through structurally related records.

Family matches are preferred; otherwise the fallback requires the same developer, model modality and declared pipeline task. No quality score or recommendation rank is used.

Same familyQwen2.5-VL-32B-Instruct

33.4527B · 128,000 tokens

Same familyQwen2.5-VL-7B-Instruct

8.29217B · 128,000 tokens

Same familyQwen2.5-VL-7B-Instruct-NVFP4

5.02952B · 128,000 tokens

FIELD-BY-FIELD RECORD

Inspect the underlying evidence.

The editorial layer above summarizes only what the verified registry can support. The sections below expose the exact fields, artifacts, source links and verification states.

WeightsLicenseHardwareFormatsLineageTrainingRuntimeSourcesVerification

01 · WEIGHTS

Exact repository artifacts

Statusverified-available
Accesspublic
RepositoryQwen/Qwen2.5-VL-3B-Instruct
Recognized weight files3
Show all 3 exact weight files
HF API file listing ↗

02 · LICENSE

License & commercial use

Declared licenseQwen Research License
License IDNot declared
Commercial useCommercial use requires a separate Qwen license
Repository license filesLICENSE

Classification describes the checked license terms; it is not legal advice.

License / model-card evidence ↗

03 · HARDWARE

Weight-memory estimate

BF16 / FP16~7.5 GB
FP8 / INT8~3.8 GB
INT4~1.9 GB

Weight-only decimal-GB estimate from total parameter count; excludes KV cache, activations, runtime overhead, optimizer state and sharding.

04 · FORMATS

Formats & precision evidence

Safetensors
BF16: observedFP16: not observedFP8: not observedINT8: not observedINT4: not observedGGUF: not observed

“Not observed” means no matching repository artifact/name/dtype signal was found; it does not prove no third-party conversion exists.

05 · LINEAGE

Base model & family

FamilyQwen2.5-VL
VariantQwen2.5-VL-3B-Instruct
Declared base modelNot declared in model-card metadata
RelationNot declared

06 · TRAINING ASSETS

Recipe & data disclosure

Training recipetraining-described-in-model-card
Data disclosurenot-disclosed-in-standard-metadata-or-obvious-model-card-section
EvaluationsNot classified by automated verifier
Intermediate checkpointsNot classified by automated verifier

07 · RUNTIME SUPPORT

Declared and mentioned runtimes

Declared libraryTransformers
Declared/taggedTransformers
Mentioned in model cardNone observed
Artifact signalsNone
Tested by Open Model WeightsNo — source-derived support only

Open Model Weights does not claim runtime compatibility unless it is declared, tagged, mentioned by the publisher, or evidenced by an artifact. No inference benchmark is implied.

08 · SOURCES

Field evidence

Primary / declared sources5
Repository revision66285546d2b8
Source policyHow evidence is classified →
model_repositoryhttps://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct
model_apihttps://huggingface.co/api/models/Qwen/Qwen2.5-VL-3B-Instruct
model_cardhttps://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct/blob/main/README.md
confighttps://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct/blob/main/config.json
licensehttps://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct/blob/main/LICENSE

09 · VERIFICATION HISTORY

Checked, not assumed

Repository revision check

listed Hugging Face source repository SHA unchanged; prior field evidence retained.

Repository revision check

listed Hugging Face source repository SHA unchanged; prior field evidence retained.

Field-by-field verification

Checked Hugging Face API metadata, exact repository file list, model card and config when accessible.

Registry record created

Previous verification level: discovered-pending.

licenseverified
commercial useclassified
contextverified
weight filesverified
formatsverified
base modelnot-declared
training recipetraining-described-in-model-card
data disclosurenot-disclosed-in-standard-metadata-or-obvious-model-card-section
runtime supportsource-derived-not-runtime-tested