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 | 2025-12-16 |
| Parameters (B) | 8.7 |
| Architecture | Vision-Language Transformer |
| Context Window | 36864 |
| Input Modalities | text, image |
| Open Source | Yes |
| License | apache-2.0 |
| Score | 5 |
| VRAM (GB) | 18 |
| Compute | 8B vision-language model requiring ~18 GB VRAM for FP16 inference; 24 GB recommended for multi-frame video. Runs on NVIDIA RTX 3090/4090 or Apple Silicon via MLX quantizations. |
| Benchmark: ARC | 89.6 |
| Benchmark: Arena-Elo | 1057 |
| Benchmark: GSM8K | 89.7 |
| Benchmark: MBPP | 57.5 |
| Benchmark: MMLU | 76.6 |
| Benchmark: MMMU | 75.8 |
| Pricing (Input) | — |
| Pricing (Output) | — |