Qwen1.5-4B-Chat
Qwen- Arena score
- 997
- Among open models
- #148of 148
- Among all on Arena
- #408
- Votes
- 7,597
Measured on Qwen1.5-4B-Chat, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
CategoryScoreOpen rankArena rankVotes
- Math1026#139#387988
- Chinese1024#131#3681K
- English1015#148#4094.8K
- Legal & government1010#141#382390
- Writing & literature1001#146#4061.9K
- Coding999#147#4021.3K
- Applied math998#141#390820
- Software & IT995#148#4082.2K
- Long prompts987#144#396692
- Hard prompts, English983#147#4061.4K
- Expert980#138#369356
- Non-English979#144#4012.8K
- Instructions978#146#4062.6K
- Multi-turn977#144#4031.1K
- Science976#146#4061.3K
- Hard prompts976#148#4082.1K
- Creative writing969#147#4091.1K
- Business & finance965#147#401738
- Medicine & health956#140#385433
- Media & sports953#147#4061.1K
- Russian952#140#381564
- German902#111#320211
- Excluding ties763#148#4095.2K
| Model | Params | Score |
|---|---|---|
| 4.0B | 997 | |
| 7.7B | 1084 | |
| 14.2B | 1128 | |
| 32.5B | 1137 | |
| 72.3B | 1166 | |
| 111B | 1175 |
About as strong, smaller
Compare
Llama-3.2-1B-InstructMeta Llama10551.2B
Built on it
Ways to run it
Most downloaded
- Qwen1.5-4B-Chat-GGUFsecond-state · Quantization1.6K downloads
- Qwen1.5-4B-Chat-i1-GGUFmradermacher · Quantization549 downloads
- Qwen1.5-4B-Chat-GGUFtensorblock · Quantization276 downloads
- Qwen1.5-4B-Chat-GGUFmradermacher · Quantization207 downloads
- Qwen1.5-4B-Chat-Q2_K-GGUFCHE-72 · Quantization96 downloads
BenchClub runs
Not runnable yet
Runs open once a Qwen1.5-4B-Chat 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 3–9B models
See more
NVIDIA-Nemotron-3-Nano-4B-BF16NVIDIA1.9M4.0B
granite-4.1-8bIBM Granite79.4K8.8B
Molmo2-8BAi247.6K8.7B
Spark-X2.6-4BXHToken32.9K4.1B