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 | 2026-02-09 |
| Parameters (B) | 16 |
| Architecture | MoE |
| Context Window | 32768 |
| Input Modalities | text |
| Open Source | Yes |
| License | apache-2.0 |
| Score | 0 |
| VRAM (GB) | 47 |
| Compute | Single GPU with ~47GB VRAM (e.g., NVIDIA RTX 6000 Ada or A6000); bf16 inference recommended via SGLang with JointThreshold decoding |
| Benchmark: AIME-2025 | 43.3 |
| Benchmark: BBH | 80.6 |
| Benchmark: C-Eval | 78.6 |
| Benchmark: DROP | 82.4 |
| Benchmark: GPQA | 53.3 |
| Benchmark: GSM8K | 86.5 |
| Benchmark: HellaSwag | 76.2 |
| Benchmark: HumanEval | 82.9 |
| Benchmark: IFEval | 83.2 |
| Benchmark: LiveCodeBench | 30.4 |
| Benchmark: MBPP | 74.1 |
| Benchmark: MMLU-Pro | 64.8 |
| Pricing (Input) | — |
| Pricing (Output) | — |