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 |
deepseek-ai
|
|---|---|
| Company | deepseek-ai |
| Release Date | 2024-01-25 |
| Parameters (B) | 7 |
| Architecture | Llama |
| Context Window | 4096 |
| Input Modalities | text |
| Open Source | Yes |
| License | other |
| Score | 0 |
| VRAM (GB) | 14 |
| Compute | Single GPU with ~14GB VRAM for BF16 inference; ~6GB with Q4 quantization |
| Benchmark: ARC | 48.1 |
| Benchmark: BBH | 53.3 |
| Benchmark: GSM8K | 72.6 |
| Benchmark: HellaSwag | 72.2 |
| Benchmark: HumanEval | 64.1 |
| Benchmark: MATH | 34.1 |
| Benchmark: MBPP | 64.6 |
| Benchmark: MMLU | 49.5 |
| Pricing (Input) | — |
| Pricing (Output) | — |