gemma-3-27b-it
GoogleBenchClub cloud
No cloud result yet
Headline numbers come from BenchClub’s pinned cloud runner.
- Arena score
- 1358
- Among open models
- #64of 148
- Among all on Arena
- #204
- Votes
- 46,608
Measured on Gemma 3 27B IT, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
CategoryScoreOpen rankArena rankVotes
- Medicine & health1392#53#1692.3K
- Science1383#58#1847.9K
- English1377#65#20223K
- Legal & government1375#57#1832.7K
- French1367#55#179655
- German1362#49#1671.2K
- Business & finance1359#58#1866.5K
- Software & IT1354#76#22714.1K
- Hard prompts, English1353#75#2258.9K
- Russian1349#59#1983.4K
- Spanish1349#65#198892
- Writing & literature1347#56#18610.6K
- Chinese1346#74#2232.8K
- Creative writing1345#50#1756.3K
- Polish1345#51#1782.8K
- Multi-turn1345#65#2116.7K
- Hard prompts1340#72#22117.7K
- Non-English1334#65#20723.6K
- Long prompts1333#66#2156.7K
- Applied math1327#77#2293.2K
- Coding1322#82#2448K
- Excluding ties1321#64#20432.6K
- Instructions1321#67#21612.5K
- Media & sports1320#61#2038K
- Math1312#77#2323.6K
- Korean1307#49#171887
- Expert1303#81#2362.3K
- Japanese1287#47#1721.1K
| Model | Params | Score |
|---|---|---|
| 1.0B | — | |
| 4.3B | 1291 | |
| 12.2B | 1334 | |
| 27.4B | 1358 |
BenchClub runs
Discussion
Built on it
Ways to run it
- GGUF · llama.cpp, Ollama, LM Studiounsloth/gemma-3-27b-it-GGUF92 builds
- MLX · Apple silicon: mlx-lm, LM StudioOutlier-Ai/gemma-3-27b-it-MLX-4bit5 builds
- AWQ · vLLM, SGLanggaunernst/gemma-3-27b-it-int4-awq4 builds
- GPTQ · vLLM, SGLangpositron-ai/google_gemma-3-27b-it-ingest-best-gptq3 builds
Most downloaded
- gemma-3-27b-it-int4-awqgaunernst · Quantization841.4K downloads
- gemma-3-27b-it-FP8-dynamicRedHatAI · Quantization63.8K downloads
- gemma-3-27b-it-GGUFunsloth · Quantization45.1K downloads
- gemma-3-27b-lenientchatfixm8than · Fine-tune45K downloads
- gemma-3-27b-it-GGUFMaziyarPanahi · Quantization37.1K downloads
More from Google
See more
gemma-4-31B-it6.3M31.3B

gemma-4-26B-A4B-it5.1M25.8B

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

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