de Google la plupart léger 2B ouvert modèle dans le Gemma 4 lineup, conçu pour resource-constrained périphérie chips.
Technical Specifications
- Provider
- Category
- open-source
- Release Date
- 2026-04
- Batch API Discount
- Standard rate
- Consumer Subscription
- Free / Self-Hosted
- Reasoning Effort Control
- Fixed
- Structured Outputs
- Yes
- Output Modalities
- text
- Official Documentation
- Visit Official Docs ↗
Data Privacy, Licensing & Deployment Governance
Official Provider Release Intelligence, API Quotas & Agentic Specs
- Official API Model ID (SDK String)
- models/gemma-4-e2b
- Supported SDK & API Protocol
- Google Gemini API (generateContent) + OpenAI-Compatible SDK
- Lifecycle & Deprecation Status
- Active GA (Guaranteed support through 2028+)
- Production Rate Limits (RPM & TPM)
- Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud
- Long-Context Pricing Tier (>128K / >200K)
- Free across full context window (only KV-cache VRAM scales)
- Prompt Cache Write & TTL Policy
- Automatic prefix KV-caching in vLLM / SGLang (0 cost)
- Computer Use & Browser GUI Agent
- Supported (Screen coordinate grounding, browser & desktop GUI action loops)
- MCP & Parallel Tool Calling
- Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema
- Web Search Grounding & Code Sandbox
- Built-in Google Search Grounding + Managed Python Code Execution Sandbox
- Fine-Tuning & Distillation Support
- Full Weights SFT, LoRA, QLoRA, DPO & GRPO RL (Unsloth / Axolotl / Llama-Factory)
- Multimodal Tokenization Billing
- Text BPE (~4 chars/token) · Vision (~258–765 tokens per image tile)
- Weights Precision & Quantization
- BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0)
- Minimum GPU VRAM Requirement
- 2 GB VRAM (4-bit Quantized) · 4 GB VRAM (Native BF16)
- Supported Inference Engines
- vLLM, SGLang, Ollama, llama.cpp, TensorRT-LLM, HuggingFace TGI
- System Card & Safety Framework
- Google DeepMind Frontier Safety Framework Verified
- Enterprise Compliance (SOC2 / HIPAA / ZDR)
- 100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control
Gemma 4 E2B Cost, Context, Hardware & API Integration
Open-weights or free-tier model: $0 API license cost when self-hosted.
Same Monthly Workload Cost Across Popular Reference Models
Live Prompt Paste Tokenizer & Cost Counter
Paste real system instructions, JSON schemas, or code to measure BPE token counts across tokenizers.
Hybrid Prompt Routing Cascade Simulator
Route routine queries to a fast lightweight model ($0.15/1M) and escalate only complex reasoning turns to Gemma 4 E2B:
Benchmark Scores & 6-Axis Capability Radar
- MMLU-Pro
- 67.2%
- HumanEval
- 76%
- Chatbot Arena Elo
- 1260pts
Strengths
- ultra-faible mémoire consumption (sous 2.5GB)
- Blazing rapide 260 tps sur grand public laptops
- à poids ouverts
Limitations & Trade-offs
- Basic raisonnement seulement
- Struggles avec convoluted multi-étapes puzzles
Editorial Assessment
Unbeatable vitesse et minimal resource usage pour petit-échelle local tâches.
Best for: Smartphones, IoT microcontrollers, et ultra-rapide local keyword/entité extractors
Compare Gemma 4 E2B
Frequently Asked Questions about Gemma 4 E2B
How much does the Gemma 4 E2B API cost per 1M tokens?+
Gemma 4 E2B by Google is priced at $0 per 1M input tokens and $0 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0 per 1M tokens, and asynchronous Batch API requests receive a 0% discount.
Should I use a $20/month subscription or the Gemma 4 E2B pay-as-you-go API?+
A flat $20/month consumer subscription is predictable for daily interactive chat and manual coding. However, if you are building software, running automated workflows, or sending low-to-moderate volume with prompt caching enabled, the pay-as-you-go API is typically far more cost-effective and offers higher rate limits without manual UI caps.
How many words and pages fit in Gemma 4 E2B's context window?+
Gemma 4 E2B features a 131K tokens context window, which equals approximately 98,304 English words or ~262 standard single-spaced pages in a single prompt. Its maximum output generation per turn is 8,192 tokens.
Can I run Gemma 4 E2B locally on my own GPU (Open Weights)?+
Yes, Gemma 4 E2B (E2B (2B)) releases open weights that can be self-hosted locally or on private cloud GPUs using vLLM, Ollama, SGLang, or llama.cpp.
Does Google train on data sent to the Gemma 4 E2B API, and is commercial use allowed?+
100% Isolated when self-hosted on private GPUs or VPC. License tier: Open-Weights Research & Commercial License. Full commercial ownership of generated outputs. Supported deployment channels include: Self-Hosted GPU (vLLM / Ollama), Private VPC, or Managed Serverless API.
How does Gemma 4 E2B perform on coding and reasoning benchmarks?+
Gemma 4 E2B achieves a composite Intelligence Index of 55/100, scoring N/A% on SWE-bench Verified, N/A% on GPQA Diamond, 67.2% on MMLU-Pro, and 1260 pts on Chatbot Arena Elo.
What is Gemma 4 E2B best used for?+
Gemma 4 E2B is best suited for: Smartphones, IoT microcontrollers, et ultra-rapide local keyword/entité extractors. Assessment: Unbeatable vitesse et minimal resource usage pour petit-échelle local tâches.
Google Family Lineage, Routing Tiers & Upgrade Path
Step down to a lighter sibling for high-volume routing or step up to Google's flagship reasoning tier:
Gemini 4 Argon
Gemini 3.8 Flash
Gemini 3.7 Flash
Gemini 3.6 Flash
Gemini 3.5 Flash-Lite
Gemini Omni Flash
AI Glossary & Architecture Concepts
View full glossary →Key machine learning concepts and benchmarks relevant to Gemma 4 E2B:
L'unité textuelle de base traitée par un modèle linguistique, représentant généralement 3 à 4 caractères ou environ 0,75 mot. Par exemple, une phrase courante est découpée en plusieurs jetons.
Une suite de tests standardisés permettant d'évaluer et de comparer objectivement les performances des modèles d'IA sur des tâches ciblées (code avec SWE-bench, mathématiques avec AIME, etc.).
Le nombre maximal de jetons qu'un modèle peut traiter simultanément (entrée et sortie comprises). Une fenêtre de 1 000 000 jetons permet d'analyser environ 750 000 mots en une seule requête.
Un modèle d'IA entraîné par apprentissage par renforcement pour allouer du temps de calcul à la réflexion logique avant d'émettre une solution, idéal pour les problèmes scientifiques et le code complexe.
Une méthode de raisonnement pas-à-pas où le modèle décompose le problème en étapes logiques intermédiaires avant de conclure, augmentant drastiquement la précision en mathématiques et programmation.
La capacité d'un LLM à déterminer quand une action externe est requise et à générer des arguments structurés pour invoquer des API, calculatrices ou bases de données avant de poursuivre.
Les scores de benchmarks, tarifs par token et limites évoluent rapidement. Vérifiez toujours les spécifications actuelles sur la documentation officielle du fournisseur.
Sources: Google DeepMind Gemma 4 Specs↗