Compare LLM Models
Select 2-5 models to compare side by side.
Select models to compare
0 / 5 selected
Top downloads
Select 2-5 models
| Attribute |
Qwen
|
|---|---|
| Company | Qwen |
| Release Date | 2025-04-29 |
| Parameters (B) | 30.5 |
| Architecture | MoE Transformer |
| Context Window | 128000 |
| Input Modalities | text |
| Open Source | Yes |
| License | apache-2.0 |
| Score | 0 |
| VRAM (GB) | 24 |
| Compute | ~61 GB model weights in BF16; 4-bit quantization runs on a single 24 GB GPU (e.g. RTX 4090), full-precision inference needs 64 GB+ VRAM (e.g. 1× H100 80 GB). Deploy via vLLM, SGLang, or llama.cpp. |
| Benchmark: AIME-2024 | 32.8 |
| Benchmark: AIME-2025 | 21.6 |
| Benchmark: C-Eval | 82.9 |
| Benchmark: GPQA-Diamond | 54.8 |
| Benchmark: IFEval | 83.7 |
| Benchmark: LiveCodeBench | 29.8 |
| Benchmark: MATH-500 | 89.8 |
| Benchmark: MMLU-Pro | 69.1 |
| Pricing (Input) | 0.12 |
| Pricing (Output) | 0.50 |