Qwen3.8-27B
QwenBenchClub cloud
No cloud result yet
Headline numbers come from BenchClub’s pinned cloud runner.
- Arena score
- 1437
- Among open models
- #19of 148
- Among all on Arena
- #85
- Votes
- 33,323
Measured on Qwen3.8-27B, 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#9Expert#10Software & IT
CategoryScoreOpen rankArena rankVotes
- Chinese1493#18#672.5K
- Coding1479#11#598.9K
- Expert1479#9#543.5K
- Software & IT1474#10#5612.8K
- French1466#11#551.2K
- Science1463#12#555.2K
- Hard prompts, English1462#11#648K
- Applied math1461#16#681.9K
- Hard prompts1456#11#6621.5K
- Math1455#18#681.6K
- English1447#17#8112.2K
- Long prompts1446#11#6914.5K
- Legal & government1446#17#782.6K
- Spanish1443#21#791.1K
- Polish1441#15#67518
- Business & finance1440#11#606K
- Medicine & health1439#31#1012.2K
- German1436#19#82526
- Multi-turn1436#22#955.2K
- Instructions1431#13#7311.7K
- Excluding ties1429#20#8924.6K
- Non-English1424#19#8821.1K
- Russian1408#31#1234.6K
- Writing & literature1401#30#1149K
- Japanese1398#17#82579
- Korean1389#20#89499
- Media & sports1388#31#1218.3K
- Creative writing1377#34#1366.9K
BenchClub runs
Discussion
1 post this week
- I ran Qwen3.8 27B on single 8GB Card! (Better than expected)Red Stapler · Aug 24, 20267.9K likes
- Qwen 3.8 27Berdaltoprak · Aug 14, 20261.4K points
- Локальная Qwen3.8:27b вместе с Hermes удивляет! #llm #ollama #hermesУ Павла! · Sep 23, 20266.5K likes
- Qwen3.8-2.4TPhilpax · Aug 12, 2026713 points
- New Deepseek, GLM 5.3, Grok 4.6, LTX 2.5, Qwen 3.8, Gemini 3.7: AI NEWSAI Search · Aug 16, 20265.1K likes
Built on it
Top 10 among open models in#1Quantizations
Ways to run it
- GGUF · llama.cpp, Ollama, LM Studiounsloth/Qwen3.8-27B-GGUF793 builds
- MLX · Apple silicon: mlx-lm, LM Studiolmstudio-community/Qwen3.8-27B-MLX-4bit485 builds
- AWQ · vLLM, SGLangnicosuter/Qwen3.8-27B-AWQ52 builds
- GPTQ · vLLM, SGLangSergiioB/Qwen3.8-27B-GPTQ-Int4-sym-G128-MTP-BF16120 builds
Most downloaded
- Qwen3.8-27B-GGUFunsloth · Quantization6.8M downloads
- Qwen3.8-27B-FP8Qwen · Quantization6.1M downloads
- Huihui-Qwen3.8-27B-abliterated-GGUFhuihui-ai · Quantization4.3M downloads
- Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUFcdiamond · Quantization3.3M downloads
- Qwen3.8-27B-MLX-4bitlmstudio-community · Quantization2.7M downloads
More from Qwen
See more
Qwen3.5-27B1.7M27.8B

Qwen3.5-35B-A3B1.4M36.0B

Qwen3.5-122B-A10B775.1K125B

Qwen3.5-397B-A17B711.9K403B
Other 20–40B models
See more
gemma-4-31B-itGoogle6.3M31.3B
Ornith-1.0-35BOrnith1.4M35.1B
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16NVIDIA1.3M31.6B
GLM-4.7-FlashZ.ai1.2M31.2B