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 |
inclusionAI
|
|---|---|
| Company | inclusionAI |
| Release Date | 2025-05-10 |
| Parameters (B) | 16.8 |
| Architecture | MoE |
| Context Window | 128000 |
| Input Modalities | text |
| Open Source | Yes |
| License | mit |
| Score | 0 |
| VRAM (GB) | 36 |
| Compute | Single NVIDIA GPU with 36GB+ VRAM for BF16 inference (e.g. A100 40GB); 24GB GPU feasible with INT4 quantization |
| Benchmark: AIME-2024 | 21.9 |
| Benchmark: BBH | 75.8 |
| Benchmark: GPQA | 36.5 |
| Benchmark: HumanEval | 87.3 |
| Benchmark: IFEval | 77.7 |
| Benchmark: LiveCodeBench | 22.7 |
| Benchmark: MATH | 82.6 |
| Benchmark: MMLU | 74.3 |
| Pricing (Input) | — |
| Pricing (Output) | — |