Gemma 4 26B A4B (Reasoning)
Open weightsOpen weightsText26B total / 4B active (MoE)Reasoning
Gemma family model by Google — reasoning.
About the Gemma family
Google's open-weight small-model family (270M to ~31B, including MoE 'A4B' and efficient E2B/E4B variants, some with reasoning modes) distilled from Gemini tech for local and on-device use.
All Gemma modelsHow this one is configured
This configuration runs in reasoning mode (thinks step-by-step before answering); mixture-of-experts with ~26B total / ~4B active parameters per token.
Who makes it
GoogleUnited StatesMaker of the Gemini frontier models and open-weight Gemma family.More from Gemma
- Gemma 3 12B Instruct
- Gemma 3 1B Instruct
- Gemma 3 270M
- Gemma 3 27B Instruct
- Gemma 3 4B Instruct
- Gemma 3n E2B Instruct
- Gemma 3n E4B Instruct
- Gemma 3n E4B Instruct Preview (May '25)
- Gemma 4 12B (Non-reasoning)
- Gemma 4 12B (Reasoning)
- Gemma 4 26B A4B (Non-reasoning)
- Gemma 4 31B (Non-reasoning)
- Gemma 4 31B (Reasoning)
- Gemma 4 E2B (Non-reasoning)
- Gemma 4 E2B (Reasoning)
- Gemma 4 E4B (Non-reasoning)
- Gemma 4 E4B (Reasoning)