Qwen3.5-35B-A3B
QwenBenchClub cloud
No cloud result yet
Headline numbers come from BenchClub’s pinned cloud runner.
- Arena score
- 1395
- Among open models
- #50of 148
- Among all on Arena
- #166
- Votes
- 30,163
Measured on Qwen3.5-35B-A3B, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
CategoryScoreOpen rankArena rankVotes
- Chinese1457#37#1182.1K
- Medicine & health1421#38#1292.3K
- Software & IT1415#51#16411.9K
- French1413#44#142872
- Science1413#48#1585.2K
- Applied math1411#48#1531.7K
- Hard prompts, English1411#50#1608.7K
- Coding1410#53#1688.3K
- Expert1408#48#1512.8K
- English1407#50#16213.4K
- Math1403#46#1571.8K
- Hard prompts1400#50#16719.1K
- Legal & government1398#48#1632.4K
- Business & finance1394#50#1556.1K
- Spanish1393#49#158989
- Multi-turn1390#52#1685.4K
- Long prompts1390#50#16911.8K
- Polish1384#41#143579
- Instructions1380#49#1629.8K
- Non-English1378#51#16816.7K
- Russian1377#50#1703.6K
- Excluding ties1373#50#16522K
- German1367#47#162487
- Writing & literature1365#48#1717K
- Korean1356#36#134486
- Media & sports1348#52#1755.9K
- Creative writing1347#47#1724.6K
- Japanese1324#42#152248
| Model | Params | Score |
|---|---|---|
| 2.3B | — | |
| 27.8B | 1409 | |
| 36.0B | 1395 | |
| 125B | 1417 | |
| 403B | 1438 |
BenchClub runs
Discussion
- Qwenputer: A functioning, deterministic RISC-V CPU inside Qwen3.5csmantle · Oct 29, 2026709 points
- How to run Qwen 3.5 locallyCuriositry · Mar 7, 2026490 points
- Kev: Tiny Jev-like family of decision models built on top of Qwen3.5tosh · Sep 21, 2026463 points
- Qwen3.5 122B and 35B models offer Sonnet 4.5 performance on local computerslostmsu · Feb 28, 2026461 points
- Qwen3.5: Towards Native Multimodal Agentsdanielhanchen · Feb 16, 2026434 points
Built on it
Ways to run it
- GGUF · llama.cpp, Ollama, LM Studiounsloth/Qwen3.5-35B-A3B-GGUF176 builds
- MLX · Apple silicon: mlx-lm, LM Studiowang-yang/Ornith-1.0-35B-MTPLX62 builds
- AWQ · vLLM, SGLangQuantTrio/Qwen3.5-35B-A3B-AWQ10 builds
- GPTQ · vLLM, SGLangQwen/Qwen3.5-35B-A3B-GPTQ-Int412 builds
Most downloaded
- AutoTrust-Decider-Pro-35Bautotrust · Fine-tune1.3M downloads
- Qwen3.5-35B-A3B-FP8Qwen · Quantization887.3K downloads
- Qwen3.5-35B-A3B-GPTQ-Int4Qwen · Quantization322.7K downloads
- Qwen3.5-35B-A3B-GGUFunsloth · Quantization317.9K downloads
- Qwen3.5-35B-A3B-Uncensored-HauhauCS-AggressiveHauhauCS · Quantization159.2K downloads
More from Qwen
See more
Qwen3.8-27B6.9M27.8B

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

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