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 | 2025-10-21 |
| Parameters (B) | 2 |
| Architecture | Vision-Language Transformer |
| Context Window | 256000 |
| Input Modalities | text, image |
| Open Source | Yes |
| License | apache-2.0 |
| Score | 0 |
| VRAM (GB) | 6 |
| Compute | ~6GB VRAM for BF16 inference with a single image; runs on consumer NVIDIA/Apple Silicon GPUs or CPU via GGUF quantization for edge and mobile deployment |
| Benchmark: AIME-2025 | 22.2 |
| Benchmark: GPQA | 42 |
| Benchmark: IFEval | 68.2 |
| Benchmark: LiveCodeBench | 20.3 |
| Benchmark: MMLU-Pro | 49 |
| Benchmark: MMMU | 53.4 |
| Benchmark: MMMU-Pro | 36.5 |
| Benchmark: TruthfulQA | 52.3 |
| Pricing (Input) | — |
| Pricing (Output) | — |