gemma-4-26B-A4B-it
GoogleBenchClub cloud
No cloud result yet
Headline numbers come from BenchClub’s pinned cloud runner.
- Arena score
- 1434
- Among open models
- #21of 148
- Among all on Arena
- #92
- Votes
- 6,069
Measured on Gemma 4 26B A4B, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
Top 10 among open models in#9Applied math
CategoryScoreOpen rankArena rankVotes
- Chinese1495#14#61523
- Applied math1476#9#49309
- Math1470#11#46387
- French1461#15#63263
- Legal & government1456#11#60414
- Software & IT1454#26#962.2K
- Hard prompts, English1448#24#911.3K
- Expert1448#24#88452
- Coding1447#33#1131.4K
- Science1445#27#93927
- English1444#20#872.2K
- Multi-turn1442#19#881.1K
- Hard prompts1439#25#993.5K
- Russian1434#17#80895
- Business & finance1429#22#841.1K
- Excluding ties1429#21#914.2K
- Long prompts1428#24#961.7K
- Medicine & health1427#35#122388
- Non-English1421#20#903.8K
- Instructions1421#22#881.7K
- Spanish1417#37#121202
- Writing & literature1407#26#1081.4K
- Media & sports1404#18#901.1K
- Creative writing1402#22#1001K
| Model | Params | Score |
|---|---|---|
| 25.8B | 1434 | |
| 31.3B | 1443 |
BenchClub runs
Discussion
- GEMMA4 DE GOOGLE - IA EN LOCAL GRATIS EN TU MOVIL#ia #ai #gemini #bigdata #data #bilbao #gemmamaxmaxdata · Aug 27, 20266.5K likes
- Google releases Gemma 4 open modelsjeffmcjunkin · Apr 2, 20261.8K points
- Gemma 4 12B: A unified, encoder-free multimodal modelrvz · Jun 3, 20261.1K points
- 🤯 ना ChatGPT, ना Gemini! Google का ये Secret AI बिना Internet चलेगा 😱 | Gemma 4 FREE!mybigguide · Oct 24, 20261K likes
- Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Macgitpusher42 · Jul 29, 2026919 points
Built on it
Top 10 among open models in#10Quantizations
Ways to run it
- GGUF · llama.cpp, Ollama, LM Studio216 builds
- MLX · Apple silicon: mlx-lm, LM Studiolmstudio-community/gemma-4-26B-A4B-it-MLX-4bit88 builds
- AWQ · vLLM, SGLangfarbodtavakkoli/OTel-2.0-Decision-26B-A4B-4bit9 builds
- GPTQ · vLLM, SGLangpositron-ai/google_gemma-4-26B-A4B-it-ingest-best-gptq6 builds
Most downloaded
- OTel-2.0-Decision-26B-A4B-4bitfarbodtavakkoli · Quantization4.1M downloads
- gemma-4-26B-A4B-it-GGUFunsloth · Quantization2.1M downloads
- Gemma-4-26B-A4B-NVFP4nvidia · Quantization1.8M downloads
- gemma-4-26B-A4B-it-AWQ-4bitcyankiwi · Quantization1.2M downloads
- gemma-4-26B-A4B-it-FP8-dynamicRedHatAI · Quantization1.1M downloads
More from Google
See more
gemma-4-31B-it6.3M31.3B

gemma-3-4b-it995.4K4.3B

gemma-3-12b-it409.4K12.2B

gemma-3-27b-it307.6K27.4B
Other 20–40B models
See more
Qwen3.8-27BQwen6.9M27.8B
Ornith-1.0-35BOrnith1.4M35.1B
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16NVIDIA1.3M31.6B
GLM-4.7-FlashZ.ai1.2M31.2B