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 | 2026-01-28 |
| Parameters (B) | 3 |
| Architecture | DeepEncoder V2 + MoE Transformer |
| Context Window | 32000 |
| Input Modalities | text, image |
| Open Source | Yes |
| License | apache-2.0 |
| Score | 0 |
| VRAM (GB) | 8 |
| Compute | NVIDIA GPU with ≥8 GB VRAM (BF16 inference), CUDA 11.8+, Python 3.12, Flash Attention 2 recommended |
| Pricing (Input) | — |
| Pricing (Output) | — |