Gemma 4 E2B（有效2B端侧模型）
Gemma 4 E2B is a multimodal foundation model developed by DeepMind. With approximately 5.1B parameters, it is designed for efficient operation on edge devices.
Parameters
5.1B
Context Window
128K
License
Apache 2.0
Release Date
2026-04
API Pricing
API pricing for this model is not yet available
Strengths
- ・Strong multimodal support
- ・128K long context window
- ・Efficient operation on edge devices
Weaknesses
- ・Smaller knowledge base than large models
- ・Limits in complex reasoning
- ・Dependency on available computational resources
Use Cases
- ・Real-time on-device processing
- ・Multimodal data analysis
- ・Long-context processing
Deep Analysis
Parameters
2.1B (effective) / 5.1B with embeddings
Smallest model in the Gemma 4 family
Context Window
128K tokens
Per Google/HuggingFace docs (gemma4.dev reports 8K for text-only mode)
Architecture
Dense transformer
With Per-Layer Embeddings (PLE) and shared KV cache
Min VRAM (BF16)
5 GB
Or 2GB with Q4 quantization
Multimodal
Image + Audio input
Supports vision and audio unlike what some sources claim
Release Date
April 2, 2026
Part of Gemma 4 family launch
License
Apache 2.0
First Gemma with Apache 2.0
Tool Use
Yes
Supports function calling and structured output
Languages
140+
Natively multilingual
Strengths
- ・Runs entirely on CPU - no GPU required for basic inference
- ・Only 2GB VRAM needed with Q4 quantization
- ・Multimodal: supports image and audio input despite tiny size
- ・128K context window for an edge model is exceptional
- ・Apache 2.0 license for maximum deployment flexibility
- ・Compatible with Ollama, llama.cpp, Transformers, MLX, WebGPU
Weaknesses
- ・No thinking mode support
- ・Limited reasoning capability compared to larger models
- ・Some sources report text-only 8K context variant (conflicting specs)
- ・Not suitable for complex multi-step reasoning tasks
- ・Quality trade-off for extreme efficiency
Competitor Comparison
| Model | Arena | SWE | GPQA | Price |
|---|---|---|---|---|
| Gemma 4 E2B (2.1B) | N/A | N/A | N/A | Free (open weights) |
| Gemma 4 E4B (4.5B) | ~1300 (est) | N/A | ~50% (est) | Free (open weights) |
| Phi-3.5 Mini (3.8B) | ~1100 | N/A | ~55% | Free (open weights) |
| SmolLM2 (1.7B) | N/A | N/A | N/A | Free (open weights) |
| Qwen2.5 (3B) | ~1050 | N/A | ~45% | Free (open weights) |
Gemma 4 E2B is the smallest model in the Gemma 4 family with 2.1B effective parameters (5.1B with embeddings). It can run entirely on CPU with as little as 2GB VRAM (Q4), supports multimodal input (image + audio), and has a 128K context window. Released April 2, 2026 under Apache 2.0 license.
Sources
Analysis generated: 2026-05-24