AI Model Radar
中文 EN

Gemma 4 26B-A4B IT

Google
Model overview

google/gemma-4-26B-A4B-it

Google's current open-weight multimodal Gemma model with a sparse active-parameter architecture.

general LLMreasoningmultimodalvision-languagelong contextchatlocal inferenceevaluationenterprise access
CompareCompanyRankingsPublic signals
Representative version

google/gemma-4-26B-A4B-it

CompanyGoogle
Release2026-04-02
Release typeModel release
Parameters26B / 4B active
ArchitectureSparse mixture-of-experts transformer
Context262,144
Input modalitiestext / image
Output modalitiestext
Tool use / function callingNot disclosed
Structured output / reasoningConfirmed: Reasoning
Vision / audio / videoConfirmed: Vision
Open weights / LicenseWeights available / Apache-2.0 (license source pending verification)
google-gemma-4-26b-a4b-it-current · License source pending verification
Vendor APIAvailable
Gemma 4 model cardgoogle-gemma-4-26b-a4b-it-current · 2026-04-02
OpenRouterOpenRouter listed
PricingOpenRouter · 2026-07-15: $0.1 / $0.3
input / output, per 1M tokens
BenchmarkNo reliable public source
Public signalsNo reliable public source
Use caseslocal inference / Multimodal assistants / research evaluation / Fine-tuning
Claim evidenceRelease / model specs / weightsGemma 4 model cardgoogle/gemma-4-26B-A4B-it · 2026-04-02
OpenRouter

Pricing / context / availability

OpenRouterOpenRouter listed
OpenRouter listinggoogle/gemma-4-26b-a4b-it
Mapped versiongoogle/gemma-4-26B-A4B-it
google-gemma-4-26b-a4b-it-current
PricingOpenRouter · 2026-07-15: $0.1 / $0.3
input / output, per 1M tokens
Context262144
Speed/LatencyNo reliable public source
Snapshot time2026-07-15T20:11:41.551Z
SourceView source
Evidence gaps

Public display boundary

No reliable benchmark sourceNo public model-card activity countersNo linkable real reviewSpeed/latency not disclosed