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 |
zai-org
|
|---|---|
| Company | zai-org |
| Release Date | 2025-04-14 |
| Parameters (B) | 32 |
| Architecture | Transformer |
| Context Window | 128000 |
| Input Modalities | text |
| Open Source | Yes |
| License | mit |
| Score | 0 |
| VRAM (GB) | 24 |
| Compute | Single NVIDIA RTX 4090 24GB (Q4 quantization) or A100 80GB for BF16 inference |
| Benchmark: AIME-2024 | 80.8 |
| Benchmark: AIME-2025 | 63.6 |
| Benchmark: GPQA-Diamond | 66.1 |
| Benchmark: HLE | 7.2 |
| Benchmark: IFEval | 84.5 |
| Benchmark: LiveCodeBench | 59.1 |
| Benchmark: MMLU-Pro | 77.4 |
| Pricing (Input) | — |
| Pricing (Output) | — |