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 | 2024-09 |
| Parameters (B) | 7 |
| Architecture | MoE |
| Context Window | 4096 |
| Input Modalities | text |
| Open Source | Yes |
| License | apache-2.0 |
| Score | 0 |
| VRAM (GB) | 16 |
| Compute | Single NVIDIA GPU with 16GB+ VRAM for BF16 inference (~15GB weights); Q4 GGUF runs on 6GB+ consumer GPUs |
| Benchmark: ARC | 62.1 |
| Benchmark: BBH | 33.6 |
| Benchmark: GPQA-Diamond | 19.7 |
| Benchmark: GSM8K | 3 |
| Benchmark: HellaSwag | 80 |
| Benchmark: IFEval | 16.6 |
| Benchmark: MMLU | 54.1 |
| Pricing (Input) | — |
| Pricing (Output) | — |