Gemma 3 4B
by Googletext+image->text2 endpoints
Neura Intelligence Index
5.7/ 100
Rank
#368—
Confidence
lowBenchmarks
2(5% coverage)
Overview
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
Capabilities
Text generation
Image understanding
Structured output
Long context
Top-P sampling
Stop sequences
Deterministic seed
Log probabilities
Modalities
Input
TextImage
Output
Text
Technical Specifications
Context Window
131.1K tokens
Max Output
16.4K tokens
Knowledge Cutoff
2024-08-31
Tokenizer
Gemini
Uptime (24h)
10000.0%
Parameters
4000000000B
License
gemmaOpen Weights
Country
🇺🇸US
Release Date
March 12, 20251y
Supported Parameters
frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetop_ktop_logprobstop_p
Benchmark Performance
general
| Benchmark | Score | Source |
|---|---|---|
| SimpleQA | 4 | verified |
reasoning
| Benchmark | Score | Source |
|---|---|---|
| GPQA Diamond | 30.8 | verified |
Performance Over Time
Pricing
Per 1M tokens
Input$0.05
Output$0.10
Added
March 13, 2025
Last synced 11/6/2026