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 | 2024-09-18 |
| Parameters (B) | 7.6 |
| Architecture | Transformer |
| Context Window | 131072 |
| Input Modalities | text |
| Open Source | Yes |
| License | apache-2.0 |
| Score | 0 |
| VRAM (GB) | 16 |
| Compute | ~16GB VRAM (BF16 full-precision inference); 4-bit quantization ~5GB; deployable locally on a single consumer GPU (e.g. RTX 3090/4090) |
| Benchmark: AIME-2024 | 10 |
| Benchmark: ARC | 60.9 |
| Benchmark: Aider | 55.6 |
| Benchmark: C-Eval | 61.4 |
| Benchmark: GPQA | 35.6 |
| Benchmark: GSM8K | 86.7 |
| Benchmark: HellaSwag | 76.8 |
| Benchmark: HumanEval | 88.4 |
| Benchmark: IFEval | 58.6 |
| Benchmark: LiveCodeBench | 18.2 |
| Benchmark: MATH | 66.8 |
| Benchmark: MBPP | 83.5 |
| Benchmark: MMLU | 68.7 |
| Benchmark: MMLU-Pro | 45.6 |
| Pricing (Input) | — |
| Pricing (Output) | — |