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 |
baichuan-inc
|
|---|---|
| Company | baichuan-inc |
| Release Date | 2023-07-08 |
| Parameters (B) | 13 |
| Architecture | Transformer |
| Context Window | 4096 |
| Input Modalities | text |
| Open Source | Yes |
| License | |
| Score | 0 |
| VRAM (GB) | 26.6 |
| Compute | NVIDIA GPU with ~27GB VRAM for FP16 inference; INT8/INT4 quantized versions run on RTX 3090 (24GB) |
| Benchmark: C-Eval | 51.5 |
| Benchmark: MMLU | 52.1 |
| Pricing (Input) | — |
| Pricing (Output) | — |