Google DeepMind: 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...
Specifications
| Attribute | Value |
|---|---|
| Lab | Google DeepMind |
| Tags | Open Weight Fast |
| Release Date | 2026-04 |
| Context Window | 262,144 tokens |
| Input Price / 1M | $0.06 |
| Output Price / 1M | $0.33 |
| Input Modalities | Image, Text, Video |
| Output Modalities | Text |
Strengths
Weaknesses
Best For
In Depth: Gemma 4 26B A4B
Summary
Gemma 4 26B A4B is an AI model from Google DeepMind.
Released 2026-04. It currently appears in the Overall category on LMRank and 1 other category. It supports Image, Text, Video input and produces Text output, with a context window of 262,144 tokens. Input pricing is $0.06 per 1M tokens and output is $0.33 per 1M tokens on OpenRouter.