Models/Google/Gemma 4 26B MoE

Gemma 4 26B MoE

Google 🧠 Language Model

Google's open-weight mixture-of-experts model — 26B total, 4B active parameters for fast inference

Specifications

Context Window262,144 tokens
Max Output32,768 tokens
Speed●●●●● Very Fast
ModalitiesInput: text  ·  Output: text
FeaturesTools: Yes Streaming: Yes

Pricing

Contact for pricing

Capabilities

tools
Use Gemma 4 26B MoE on Zubnet →

More from Google

Gemini 2.5 Flash
Fast and efficient model with adaptive thinking for complex tasks
🧠 Language Model
Gemini 2.5 Flash-Lite
Cost-efficient high-throughput model for budget-conscious applications
🧠 Language Model
Gemini 2.5 Pro
Enhanced thinking and reasoning for complex problems
🧠 Language Model
Gemma 4 31B
Google's open-weight dense model with 262K context and strong multilingual reasoning
🧠 Language Model