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 |
allenai
|
|---|---|
| Company | allenai |
| Release Date | 2025-12-11 |
| Parameters (B) | 7 |
| Architecture | Vision-Language Transformer |
| Context Window | 65536 |
| Input Modalities | text, image |
| Open Source | Yes |
| License | apache-2.0 |
| Score | 0 |
| VRAM (GB) | 24 |
| Compute | 24GB+ GPU for image QA in bfloat16; single NVIDIA A100 80GB (or H100) recommended for video inference with long context up to 65,536 tokens |
| Benchmark: ARC | 79.9 |
| Benchmark: GSM8K | 89 |
| Benchmark: MBPP | 55.7 |
| Benchmark: MMLU | 64.1 |
| Benchmark: MMMU | 45.8 |
| Pricing (Input) | — |
| Pricing (Output) | — |