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 | 2025-04-28 |
| Parameters (B) | 1.7 |
| Architecture | Transformer |
| Context Window | 32768 |
| Input Modalities | text |
| Open Source | Yes |
| License | apache-2.0 |
| Score | 0 |
| VRAM (GB) | 4 |
| Compute | Consumer GPU with 4GB+ VRAM for FP16 inference (~3.8GB); ~1GB with Q4 quantization. Suitable for edge devices and resource-constrained fine-tuning. |
| Benchmark: BBH | 54.5 |
| Benchmark: GPQA | 28.3 |
| Benchmark: GSM8K | 75.4 |
| Benchmark: MATH | 43.5 |
| Benchmark: MBPP | 55.4 |
| Benchmark: MMLU | 62.6 |
| Benchmark: MMLU-Pro | 36.8 |
| Pricing (Input) | — |
| Pricing (Output) | — |