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 | 2025-09-17 |
| Parameters (B) | 100 |
| Architecture | MoE |
| Context Window | 128000 |
| Input Modalities | text |
| Open Source | Yes |
| License | mit |
| Score | 0 |
| VRAM (GB) | 160 |
| Compute | 2x NVIDIA A100/H100 80GB GPUs with tensor parallelism (vLLM); FP8 weights reduce memory; 200+ tokens/s on H20 |
| Benchmark: AIME-2024 | 70.0 |
| Benchmark: AIME-2025 | 55.8 |
| Benchmark: Aider | 71.2 |
| Benchmark: C-Eval | 87.9 |
| Benchmark: GPQA-Diamond | 68.1 |
| Benchmark: HLE | 5.0 |
| Benchmark: IFEval | 81.5 |
| Benchmark: LiveCodeBench | 51.4 |
| Benchmark: MBPP | 94.2 |
| Benchmark: MMLU-Pro | 77.1 |
| Pricing (Input) | — |
| Pricing (Output) | — |