Google: Gemma 4 26B A4B IT
Google's compact Gemma 4 mixture-of-experts model with 4B active parameters. Fast and inexpensive for chat, extraction and image understanding, with tool calling and optional reasoning. Served here with a context of about 31,000 tokens.
- Maker
- Model ID
google/gemma-4-26b-a4b-it- Context length
- 256,000 tokens
- Input
- images and text
- Output
- text
- Capabilities
- tool calling, structured output, and reasoning
Providers
- Grunden.AI: Data centers: Sweden; Sovereign EU
- Scaleway: Data centers: France; Sovereign EU
Facts as Markdown · Quickstart
More models by Google
- Google: Gemma 4 31B IT Google · 262,144 tokens · text
More Text models
- DeepSeek: DeepSeek V4 Flash 0731 DeepSeek · 256,000 tokens · text
- DeepSeek: DeepSeek V4 PRO 0813 DeepSeek · 1,048,576 tokens · text
- DeepSeek: DeepSeek V4.1 Flash DeepSeek · 1,048,576 tokens · text
- DeepSeek: DeepSeek V4.1 Flash 1017 DeepSeek · 1,048,576 tokens · text
- Meta: Llama 3.3 70B Instruct Meta · 131,072 tokens · text
- MiniMax: MiniMax M3 MiniMax · 1,048,576 tokens · text