Together AI - Gemma 3n-e4B
Open Source
About
Efficient 4B parameter model from Google, available on Together AI. Gemma 3 nano-edge model optimized for low-latency inference.
Capabilities
VisionMultimodalReasoningFunction CallingTool UseJSON ModeCode Execution
Providers(1)
| Provider | Input (per 1M) | Output (per 1M) | Type | |
|---|---|---|---|---|
| Together AI | $0.02 | $0.04 | Serverless |
Rankings
Compare
All comparisons →Together AI - Gemma 3n-e4B vs Qwen2 7B InstructTogether AI - Gemma 3n-e4B vs ShieldGemma 9BTogether AI - Gemma 3n-e4B vs Dracarys Llama 3.1 70B InstructTogether AI - Gemma 3n-e4B vs Gemma 2 9B SahabatAI InstructTogether AI - Gemma 3n-e4B vs Llama 3 Taiwan 70B InstructTogether AI - Gemma 3n-e4B vs Llama 3 Swallow 70B InstructTogether AI - Gemma 3n-e4B vs Llama 3.1 Swallow 8B InstructTogether AI - Gemma 3n-e4B vs Bielik 11B v2.6 InstructTogether AI - Gemma 3n-e4B vs Sarvam-M Multilingual HybridTogether AI - Gemma 3n-e4B vs Teuken 7B InstructTogether AI - Gemma 3n-e4B vs Italia 10B InstructTogether AI - Gemma 3n-e4B vs Colosseum 355B InstructTogether AI - Gemma 3n-e4B vs Stockmark 2 100B InstructTogether AI - Gemma 3n-e4B vs Seed-OSS 36B InstructTogether AI - Gemma 3n-e4B vs Marin 8B InstructTogether AI - Gemma 3n-e4B vs Granite Guardian 3.0 8B
Specifications
FamilyGemma 3
Released2026-03-15
Parameters4B
Context8192
ArchitectureDecoder Only
Specializationgeneral
Trainingpretraining