Qwen3-235B-A22B-Instruct-2507
Qwen- Arena score
- 1419
- Among open models
- #36of 148
- Among all on Arena
- #123
- Votes
- 97,593
Measured on Qwen3-235B-A22B-Instruct (2507), the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
CategoryScoreOpen rankArena rankVotes
- Chinese1465#28#997.2K
- Software & IT1447#33#11134.7K
- Medicine & health1445#27#885.9K
- Coding1445#34#11521.6K
- French1445#25#962.1K
- Expert1442#28#966.4K
- Applied math1441#26#905.2K
- Science1437#31#11115.7K
- Hard prompts, English1436#34#11622.6K
- Hard prompts1433#29#10853.2K
- Multi-turn1432#23#10117K
- German1432#21#861.8K
- Math1431#28#1006K
- Spanish1429#30#1032.9K
- Legal & government1429#31#1166.6K
- Long prompts1426#26#10326.9K
- English1424#42#13240.8K
- Business & finance1418#32#10718.2K
- Russian1411#30#12010.1K
- Non-English1409#28#11056.7K
- Instructions1408#29#11227.7K
- Excluding ties1408#33#11969.5K
- Polish1407#32#1203.9K
- Japanese1400#16#801.4K
- Korean1390#18#861.8K
- Writing & literature1390#34#13422K
- Creative writing1375#36#14013.8K
- Media & sports1374#35#13717.9K
| Model | Params | Score |
|---|---|---|
| 752M | — | |
| 2.0B | — | |
| 4.0B | — | |
| 4.0B | — | |
| 8.2B | — | |
| 14.8B | — | |
| 30.5B | 1317 | |
| 30.5B | 1384 | |
| 32.8B | 1340 | |
| 235B | 1394 | |
| 235B | 1419 |
About as strong, smaller
Compare
gemma-4-26B-A4B-itGoogle143425.8B

Qwen3.8-27BQwen143727.8B

Qwen3.5-27BQwen140927.8B

gemma-4-31B-itGoogle144331.3B
Discussion
- За считанные минуты локальная ИИ модель моделирует корпус для ESP32C3 #ai #qwen3У Павла! · Oct 27, 202612.3K likes
- Qwen3-TTS family is now open sourced: Voice design, clone, and generationPalmik · Jan 22, 2026744 points
- Orthrus-Qwen3: up to 7.8×tokens/forward on Qwen3, identical output distributionFranckDernoncou · May 15, 2026246 points
- How to Clone Voice Locally in Any Language for Free with Qwen3 TTSUmair Alam Chaudhry · Aug 23, 2026167 likes
- Good results fine tuning a local LLM like Qwen 3:0.6B to categorize questionsdev-experiments · Jun 21, 2026215 points
Built on it
Ways to run it
- GGUF · llama.cpp, Ollama, LM Studiounsloth/Qwen3-235B-A22B-Instruct-2507-GGUF16 builds
- MLX · Apple silicon: mlx-lm, LM Studiomlx-community/Qwen3-235B-A22B-Instruct-2507-4bit18 builds
- AWQ · vLLM, SGLangQuantTrio/Qwen3-235B-A22B-Instruct-2507-AWQ4 builds
- GPTQ · vLLM, SGLangQuantTrio/Qwen3-235B-A22B-Instruct-2507-GPTQ-Int4-Int8Mix1 build
Most downloaded
- Qwen3-235B-A22B-Instruct-2507-GGUFunsloth · Quantization28.7K downloads
- Qwen3-235B-A22B-Instruct-2507-FP8Qwen · Quantization19K downloads
- Qwen_Qwen3-235B-A22B-Instruct-2507-GGUFbartowski · Quantization8.5K downloads
- Qwen3-235B-A22B-Instruct-2507-AWQQuantTrio · Quantization4.1K downloads
- Qwen3-235B-A22B-Instruct-2507-4bitmlx-community · Quantization2.1K downloads
BenchClub runs
Not runnable yet
Runs open once a Qwen3-235B-A22B-Instruct-2507 build is registered.
More from Qwen
See more
Qwen3.8-27B6.9M27.8B

Qwen3.5-27B1.7M27.8B

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

Qwen3.5-122B-A10B775.1K125B
Other 80–300B models
See more
DeepSeek-V4-FlashDeepSeek1.2M291B

MiniMax-M2.5MiniMax1M229B
Inkling-SmallThinking Machines1M266B
Hy3Tencent987.2K299B