Gemma 4 E2B IT
gemma-4-e2b-it
Last refreshed 2026-05-11. Next refresh: weekly.
Gemma 4 E2B IT is worth evaluating for rag, agents, and long context when its provider route and context window match the workload.
Decision context: Classification task fit, 2 tracked provider routes, and research from 2026-04-21.
Use it for
- Teams evaluating rag, agents, and long context
- Workloads that can use a 128k context window
- Buyers comparing 2 tracked provider routes
Do not use it for
- Workloads where another current model has stronger sourced task evidence
Cheapest output
Free
GCP Vertex AI per 1M tokens
Provider routes
2
Tracked API hosts
Quality / dollar
Grade A
Ranked by benchmark score divided by cheapest output price
Freshness
2026-04-21
Researched 27d ago
Top use-case fit
RAG
Included by capability and metadata signals in the decision map.
Agents
Included by capability and metadata signals in the decision map.
Long context
Included by capability and metadata signals in the decision map.
Provider price ladder
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| GCP Vertex AI | Free | Free | Serverless |
| Google AI Studio | - | - | ServerlessPartial |
Benchmark peer barsfor Classification
Migration checks
No linked migration route is available for this model yet.
About
Instruction-tuned variant of Gemma 4 E2B for edge deployment with enhanced instruction-following capabilities.
Gemma 4 E2B IT has a 128K-token context window.
Gemma 4 E2B IT input tokens at $0/1M, output at $0/1M.
Capabilities
Benchmark Scores(2)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| Google-Proof Q&A | 43.4 | diamond | https://huggingface.co/google/gemma-4-e2b-it |
| MMLU PRO | 60.0 | — | https://huggingface.co/google/gemma-4-e2b-it |
