Gemma 4
Google Gemma 4 is an open-weight multimodal model family built for advanced reasoning, coding, agentic workflows, and efficient local deployment from phones to workstations.
Official Gemma 4 benchmark results
Google reports strong results for the 31B instruction-tuned model across reasoning, coding, agents, vision, and long-context evaluation.
MMLU Pro
85.2%Advanced knowledge and reasoning score for Gemma 4 31B.
AIME 2026
89.2%Competition mathematics without tools for Gemma 4 31B.
LiveCodeBench v6
80.0%Code-generation benchmark score for Gemma 4 31B.
GPQA Diamond
84.3%Graduate-level science reasoning score for Gemma 4 31B.
Tau2
76.9%Average agentic task score across three domains for Gemma 4 31B.
MMMU Pro
76.9%Multimodal reasoning score for Gemma 4 31B.
Scores come from Google’s Gemma 4 model card. Vendor-reported benchmark settings differ, so evaluate the model on your own prompts, hardware, and workflows.
Where Gemma 4 fits
The right Gemma 4 variant depends on the quality, modality, privacy, latency, and hardware requirements of your workflow.
Local coding assistants
Run code generation, completion, correction, and repository analysis on your own workstation.
Private document analysis
Process long documents, images, charts, and OCR tasks locally when data control matters.
On-device multimodal apps
Use E2B or E4B for efficient image, audio, and text experiences on edge hardware.
Tool-using agents
Build agent workflows with function calling, structured output, system instructions, and configurable thinking.
Choose a Gemma 4 model for your hardware
The family scales from efficient on-device models to larger dense and Mixture-of-Experts models for laptops, consumer GPUs, and workstations.
| Model | Architecture | Context | Modalities | Best for |
|---|---|---|---|---|
| Gemma 4 E2B | 2.3B effective dense | 128K | Text, image, audio | Phones and edge devices |
| Gemma 4 E4B | 4.5B effective dense | 128K | Text, image, audio | Edge devices and lightweight local AI |
| Gemma 4 12B | 11.95B unified dense | 256K | Text, image, audio | Multimodal agents on laptops |
| Gemma 4 26B A4B | 25.2B MoE, 3.8B active | 256K | Text, image | Fast workstation inference |
| Gemma 4 31B | 30.7B dense | 256K | Text, image | Maximum quality and fine-tuning |
Efficient by design across five model sizes
Gemma 4 uses several architecture strategies to balance reasoning quality, multimodal capability, speed, and memory use.
Hybrid attention
Local sliding-window attention is interleaved with global attention to reduce memory use while preserving long-context awareness.
Dense and MoE options
Choose dense models for straightforward quality scaling or the 26B A4B MoE model for speed with only 3.8B active parameters.
Unified 12B multimodality
Gemma 4 12B projects image patches and raw audio into one decoder-only transformer without separate multimodal encoders.
Quantization-aware checkpoints
Google provides QAT checkpoints designed to reduce memory requirements and improve practical local deployment.
Gemma 4 FAQs
Run Google Gemma 4 AI in a hosted MyClaw agent
Use MyClaw to run always-on AI agents with files, tools, browser-ready execution, and managed infrastructure.
Run Gemma 4 in MyClaw