Google: Gemma 4 26B A4B
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
Specification
- Model ID
- google/gemma-4-26b-a4b-it
- Weight license
- Not verified; consult the exact publisher model card
- Modality
- Text+image+video >text
- Context
- 262.1K tokens
- Input
- $0.068/1M
- Output
- $0.225/1M
- Updated
- Nov 14, 2026
Scores
Capabilities
- Supports tool calling
- Supports vision inputs
- Supports long-context workflows
- Supports deeper reasoning tasks
Input and output
Accepts Image, Text, Video inputs. Returns Text outputs.
Supported parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_completion_tokensmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Related models
Build with Google: Gemma 4 26B A4B
Describe what you want to make and pick this model in the composer. A database and hosting are included.