- Open models
- 16
- Downloads, last 30 days
- 14M
- Likes
- 23.9K
- Top Arena score
- 1443
Model families
Models
| Model | Score | Downloads |
|---|---|---|
| 1443 | 6.3M | |
| 1434 | 5.1M | |
| 1306 | 9.3K | |
| — | 200.4K | |
| 1334 | 409.4K | |
| 1358 | 307.6K | |
| 1291 | 995.4K | |
| 1156 | 196.3K | |
| 1207 | 148.9K | |
| 1231 | 22.9K | |
| 1094 | 5.2K | |
| 1022 | 4.9K | |
| 1056 | 26.9K | |
| — | 208K | |
| — | 63.8K | |
| 1002 | 15.5K |
API tokens per day
Last 7 days813.4B tokens−4% compared with the 7 days beforeSource: OpenRouter (openrouter.ai/rankings), as of 2026-11-17.
Built on their models
- Quantizations
- 2,768
- Fine-tunes
- 5,544
- Adapters
- 36,921
- Merges
- 178
Discussed, last 90 days
- GEMMA4 DE GOOGLE - IA EN LOCAL GRATIS EN TU MOVIL#ia #ai #gemini #bigdata #data #bilbao #gemma

gemma-4-31B-it· Aug 276.5K likes
- 🤯 ना ChatGPT, ना Gemini! Google का ये Secret AI बिना Internet चलेगा 😱 | Gemma 4 FREE!

gemma-4-31B-it· Oct 241K likes
- Gemma-4-26B-A4B with 39-69% less thinking at same accuracy

gemma-4-31B-it· Oct 23127 points
- Comparativa LLM Local: Llama 3.1 vs Gemma 4 vs Qwen 3.8 ¿Cuál es el MEJOR?

gemma-4-31B-it· Sep 7205 likes
- Show HN: Maple – Sub-2-BPW Moe Pruning to Run Gemma 4 26B at 45 TPS on a 6GB GPU

gemma-4-31B-it· Nov 821 points