Gemma 4
Open SourceGoogle•Released on 2026-04-02
Google's most capable open model family. Four sizes optimized for local hardware: E2B and E4B for mobile/edge devices, 26B MoE for speed, 31B Dense for quality. Built on Gemini 3 technology with Apache 2.0 license. Supports 140+ languages, native function calling, agentic workflows, and multimodal input.
83
Overall Score
Core Specs
256K
Context Window
8K
Max Output
✓
Reasoning
✓
Open Source
Multimodal Support
textimagevideoaudio
Scenario Scores
User Feedback Highlights
Based on community feedback. Hover to see original reviews.
− Context window smaller than cloud Gemini (256K vs 1M)+ Native multimodal: text, image, video, audio+ Apache 2.0 open-source license (major upgrade from Gemma 3)+ Agentic workflow ready (function calling, JSON output)− Brand new release - ecosystem still developing+ Four sizes covering mobile to workstation+ 26B MoE activates only 3.8B params (fast inference)+ 140+ language support− Larger models require significant hardware (80GB GPU unquantized)
Sentiment:👍 80%😐 20%👎 0%
Pros & Cons
Pros
- +Apache 2.0 open-source license (major upgrade from Gemma 3)
- +Four sizes covering mobile to workstation
- +26B MoE activates only 3.8B params (fast inference)
- +Native multimodal: text, image, video, audio
- +140+ language support
- +Agentic workflow ready (function calling, JSON output)
Cons
- −Larger models require significant hardware (80GB GPU unquantized)
- −Context window smaller than cloud Gemini (256K vs 1M)
- −Brand new release - ecosystem still developing
Reliability
Incidents (30d)0
Self-hosted model. Also available via Google AI Studio.
Pricing
Input (per 1M tokens)$0.00
Output (per 1M tokens)$0.00
Free trial available
Updated on 2026-04-03
Get Started
1Visit the provider's website
2Create an account
3Start using the model
Compare with Others
Benchmarks
arenaElo#3 open model%
mmlu%
humanEval%
arcAgi2%
note31B Dense ranks #3 open model on Arena AI leaderboard (behind GLM-5, Kimi 2.5)%