google/gemma-4-26B-A4B-it
TEXT GENERATIONConcurrency Cost:2Model Size:26BQuant:FP8Ctx Length:32kPublished:Mar 11, 2026License:apache-2.0Architecture:Transformer0.5K Open Weights Warm

The google/gemma-4-26B-A4B-it is a 25.2 billion total parameter Mixture-of-Experts (MoE) model from Google DeepMind's Gemma 4 family, featuring 3.8 billion active parameters for efficient inference. This multimodal model processes text, image, and video inputs, generating text outputs, and is optimized for reasoning, coding, and agentic workflows. It supports a 256K token context window and includes native function-calling and system prompt support, making it suitable for complex, long-context tasks.

Loading preview...

Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p