Open Model Weights
Home / Models / diffusiongemma-26B-A4B-it

GOOGLE · FIELD-VERIFIED

diffusiongemma-26B-A4B-it

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 →Field-verified 2026-10-03Machine-readable JSON ↗
DeveloperGoogle
Parameters25.8238B
Context262,144 tokens
Weight files12
LicenseApache-2.0
Accesspublic
Evidence statusSource-first verified
Repository revision checked2026-10-03
Full field verification2026-10-02
Source policy →Methodology →

MODEL INTELLIGENCE · SOURCE-FIRST

What is diffusiongemma-26B-A4B-it?

OMW evidence review3 Oct 2026

Open Model Weights records diffusiongemma-26B-A4B-it as a 25.8238B-parameter image + text → text open-weight model in the diffusiongemma family, with Google listed as the developer. The checked source repository provides 12 recognized weight artifacts, format evidence for Safetensors and a verified context window of 262,144 tokens. Values that are not evidenced in the checked sources remain explicitly undisclosed or unknown.

The repository declares Apache-2.0. Commercial use allowed under Apache-2.0 conditions. 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 and a data-disclosure signal 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 / FP16~51.6 GB
FP8 / INT8~25.8 GB
INT4~12.9 GB
FIELD EVIDENCE MAP
WeightsVerified
LicenseVerified
Commercial useClassified
ContextVerified
FormatsVerified
LineageNot declared
Training recipeTraining described in model card
Training dataDescribed in model card
RuntimeSource-derived · not runtime-tested

LICENSE & USE

Apache-2.0

Commercial use allowed under Apache-2.0 conditions

Declared licenseApache-2.0
ClassificationAllowed
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 RECORDdiffusiongemma-26B-A4B-itdiffusiongemma
TRAINING DISCLOSURE
Training recipeTraining described in model card
Training dataDescribed in model card
Familydiffusiongemma

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/google/diffusiongemma-26B-A4B-itInspect source ↗PrimaryModel Apihttps://huggingface.co/api/models/google/diffusiongemma-26B-A4B-itInspect source ↗PrimaryModel Cardhttps://huggingface.co/google/diffusiongemma-26B-A4B-it/blob/main/README.mdInspect source ↗PrimaryConfighttps://huggingface.co/google/diffusiongemma-26B-A4B-it/blob/main/config.jsonInspect source ↗Primary Or DeclaredLicensehttps://ai.google.dev/gemma/docs/gemma_4_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 and model modality. No quality score or recommendation rank is used.

Same developergemma-3-4b-it

4.30008B · 128,000 tokens

Same developergemma-4-26B-A4B-it

25.8059B · 262,144 tokens

Same developergemma-4-31B

32.6824B · 262,144 tokens

Same developergemma-4-31B-it

31.2731B · 262,144 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
Repositorygoogle/diffusiongemma-26B-A4B-it
Recognized weight files12
Show all 12 exact weight files
HF API file listing ↗

02 · LICENSE

License & commercial use

Declared licenseApache-2.0
License IDapache-2.0
Commercial useCommercial use allowed under Apache-2.0 conditions
Repository license filesNone observed

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

License / model-card evidence ↗

03 · HARDWARE

Weight-memory estimate

BF16 / FP16~51.6 GB
FP8 / INT8~25.8 GB
INT4~12.9 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

Familydiffusiongemma
Variantdiffusiongemma-26B-A4B-it
Declared base modelNot declared in model-card metadata
RelationNot declared

06 · TRAINING ASSETS

Recipe & data disclosure

Training recipetraining-described-in-model-card
Data disclosuredescribed-in-model-card
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 revisionf7f5b7f5fa82
Source policyHow evidence is classified →
model_repositoryhttps://huggingface.co/google/diffusiongemma-26B-A4B-it
model_apihttps://huggingface.co/api/models/google/diffusiongemma-26B-A4B-it
model_cardhttps://huggingface.co/google/diffusiongemma-26B-A4B-it/blob/main/README.md
confighttps://huggingface.co/google/diffusiongemma-26B-A4B-it/blob/main/config.json
licensehttps://ai.google.dev/gemma/docs/gemma_4_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 disclosuredescribed-in-model-card
runtime supportsource-derived-not-runtime-tested