Loading…
Loading…
Models / DeepSeek-Prover-V2
GPU memory needed (smallest version of each): DeepSeek-Prover-V2 671B about 783.2 GB. The cheapest runs on 8x Nvidia H200 from $45.23/h right now.
1 model (671B) · ↓ 1.1K downloads a month · from $45.23/h on 8x Nvidia H200 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-Prover-V2-671B | vLLM | 689 GB | 783.2 GB | $45.23/h 8x Nvidia H200 |
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").