Loading…
Loading…
Models / DeepSeek-V2-Lite
2 models (~15.7B to ~15.7B) · ↓ 248.6K downloads a month · from $0.45/h on Nvidia A40 right now. Each model's versions do the same job; quantized ones (AWQ, FP8, 4-bit) need less GPU memory and run on cheaper machines.
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originaldeepseek-ai/DeepSeek-V2-Lite | vLLM | 31 GB | 39.1 GB | $0.45/h Nvidia A40 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originaldeepseek-ai/DeepSeek-V2-Lite-Chat | vLLM | 31 GB | 39.1 GB | $0.45/h Nvidia A40 |
Model details come from Hugging Face and are refreshed daily; prices follow the live offers. GPU memory is GridPup's estimate: the weights, room for an 8,192-token conversation (chat models) and the runtime's own memory. Large models are split across the GPUs of one machine ("4x RTX 4090").