Gemma 4 26B
on-demand
Hosted on our own DGX Spark in Austria, available through an OpenAI-compatible API.
77
Logic Index · no budget field
36 t/s
tokens per second here
€ 0.50 / € 2
euros per M tokens, input / output
10M free tokens
Try Gemma 4 26B for free
Every new account starts with 10M free tokens, usable for this and every other model. No card, no subscription.
Fact sheet
- Model name in the API
- gemma4:26b
- Size
- 26B / 4B MoE (Q4_K_M)
- Context
- 256K
- Input
- Text, Image
- Capabilities
- ToolsImageReasoning
- License
- Apache 2.0
- Tier
- Standard
- Hosting
- loaded on demand
Call
OpenAI-compatible. The alias works as model name too.
{
"model": "gemma4:26b",
"messages": [ … ]
}
Logic Index
All models in the Logic Index →By test area
Reasoning chains
87
Logic vs. world knowledge
100
Logic grid puzzles
44
Consistency: same answer in every run for 100% of tasks.
Runs under Ollama without an adjustable thinking budget and thinks long on hard tasks. In the puzzle part every deduction is a stop at our 10-minute time limit (55 of 120 puzzles), not a single wrong answer.