Google: Gemma 4 26B A4B (free)
The Google Gemma 4 26B A4B is an AI model that supports multiple input modalities, including images, text, and video. It can process context of up to 262144 tokens, and its architecture allows for tools and reasoning capabilities. For those on a tight budget or with basic needs, the Google Gemma 4 26B A4B may be worth shortlisting due to its free pricing model. While its benchmark blended score of 57.7 across three independent benchmarks is respectable but not exceptional, it remains a viable option for users seeking an affordable solution that still provides decent performance.
Benchmark results
Independent, published benchmarks. Blended score 57.7 across 3 benchmarks, last refreshed 2026-09-06. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 31.6 |
| AI Index Coding | software engineering tasks | 64.9 |
| EQ-Bench | emotional understanding in dialogue | 70.0 |
- Model ID
- google/gemma-4-26b-a4b-it:free
- Vendor
- Released
- April 2026
- Tokenizer
- Gemma
- Input Modalities
- image, text, video
- Output Modalities
- text
- Max Output
- 32,768 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- no
Strong choice for
Category rankings
Where Google: Gemma 4 26B A4B (free) places across the 5 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #4 | Cheap Bulk InferenceCost · of 25 ranked | 138 |
| #6 | Social Media PostsWriting · of 25 ranked | 120 |
| #6 | Voice Assistant BackendVoice · of 25 ranked | 124 |
| #6 | Self-Hosted / LocalCost · of 25 ranked | 118 |
| #12 | Real-Time ChatLatency · of 25 ranked | 118 |
Similar models
Google: Gemini 3.8 Flash
Google: Gemini 3.8 Flash (batch)
Google: Gemini 3.7 Flash
Google: Gemini 3.7 Flash (batch)
Google: Gemini 3.6 Flash
Google: Gemini 3.6 Flash (batch)
Quick answers
- Is Google: Gemma 4 26B A4B (free) free to use?
- Yes. It is currently listed at no cost per token via OpenRouter, subject to provider rate limits.
- What is Google: Gemma 4 26B A4B (free)'s context window?
- 262,144 tokens, roughly 393 pages of text in a single request.
- Does Google: Gemma 4 26B A4B (free) support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can Google: Gemma 4 26B A4B (free) process images?
- Yes, it accepts image input.