Gemma 3 4B
LegacyAffordableCompact open model for efficient on-device or edge deployment.
Small footprint with multimodal vision input and broad language support. Superseded by Gemma 4 series.
▼
Gemma 3 4B is somewhat expensive at $0.05/M tokens input and $0.10/M tokens output. The model supports vision/image input, a 131K context window.
Benchmarks
This model hasn't been evaluated by Artificial Analysis yet. Benchmark scores will appear once they're published.
Specifications
Performance
Providers
Misc
Compare with
GPT 5.6 Solvs Gemma 3 4BGPT 5.6 Lunavs Gemma 3 4B
Claude Fable 5vs Gemma 3 4BClaude Opus 4.8vs Gemma 3 4BClaude Sonnet 5vs Gemma 3 4BClaude Haiku 4.5vs Gemma 3 4B
Gemini 3.6 Flashvs Gemma 3 4BGemini 3.5 Flashvs Gemma 3 4BGemini 3.5 Flash-Litevs Gemma 3 4BGemma 4 31Bvs Gemma 3 4B
Grok 4.5vs Gemma 3 4BGrok Build 0.1vs Gemma 3 4BGrok 4.1 Fastvs Gemma 3 4B
Muse Spark 1.1vs Gemma 3 4B
DeepSeek V4 Provs Gemma 3 4BDeepSeek V4 Flashvs Gemma 3 4B
MiniMax M3vs Gemma 3 4B
GLM 5.2vs Gemma 3 4B
Qwen3.7 Maxvs Gemma 3 4BQwen3.7 Plusvs Gemma 3 4BQwen3 Coder Nextvs Gemma 3 4B
Nemotron 3 Ultravs Gemma 3 4B
Mistral Small 4vs Gemma 3 4BFrequently Asked Questions about Gemma 3 4B▼
When was Gemma 3 4B released?
▼
Gemma 3 4B was released on March 13, 2025.
Who created Gemma 3 4B?
▼
Gemma 3 4B was created by Google.
How much does Gemma 3 4B cost?
▼
Gemma 3 4B costs $0.05/M input tokens and $0.10/M output tokens.
What is Gemma 3 4B API pricing?
▼
The Gemma 3 4B API is priced at $0.05 per million input tokens and $0.10 per million output tokens. You can access Gemma 3 4B through idapt.app alongside 200+ other AI models in one workspace.
Is Gemma 3 4B a reasoning model?
▼
No, Gemma 3 4B is not a reasoning model. It responds directly without an extended internal thinking step. For tasks requiring deep chain-of-thought reasoning, consider models like Claude, o-series from OpenAI, or Gemini Thinking.
Does Gemma 3 4B support image or vision input?
▼
Yes, Gemma 3 4B supports vision/image input. You can share images in your conversation and the model will analyze and respond based on their content.
Does Gemma 3 4B support audio?
▼
No, Gemma 3 4B does not support audio input.
What is the context window of Gemma 3 4B?
▼
Gemma 3 4B has a context window of 131K tokens, meaning it can process approximately 98,304 words of context at once.
Is Gemma 3 4B open source?
▼
Gemma 3 4B is a proprietary model developed by Google. The model weights and training data are not publicly available.
What is Gemma 3 4B good at?
▼
Based on benchmark data, Gemma 3 4B excels at: visual analysis and image understanding. It is Google's capable model suitable for a wide range of tasks.
Where can I use Gemma 3 4B?
▼
You can chat with Gemma 3 4B on idapt.app — no separate API key required. idapt is an AI workspace with 200+ models, agents, computers, and tasks. You can also access Gemma 3 4B through Google's own API or platform.