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 |
HuggingFaceTB
|
|---|---|
| Company | HuggingFaceTB |
| Release Date | 2024-07-16 |
| Parameters (B) | 1.7 |
| Architecture | Transformer |
| Context Window | 2048 |
| Input Modalities | text |
| Open Source | Yes |
| License | apache-2.0 |
| Score | 0 |
| VRAM (GB) | 3.4 |
| Compute | Single GPU with ~4 GB VRAM for BF16 inference; runs on CPU; INT4 quantization ~1 GB |
| Benchmark: ARC | 43.7 |
| Benchmark: BBH | 25.7 |
| Benchmark: GSM8K | 4.6 |
| Benchmark: HellaSwag | 55.5 |
| Benchmark: IFEval | 23.1 |
| Benchmark: MMLU-Pro | 11.7 |
| Pricing (Input) | — |
| Pricing (Output) | — |