// RUN ON DATACENTER GPU

Run DeepSeek-V2 (MoE-236B) on Datacenter GPU hardware

3 options ranked by estimated speed at Q4 / 8k context.

HardwareEst tok/sFits 8k?Max ctx~Price
NVIDIA B200 โ†’ ~52.7 yes 82k โ€”
AMD Instinct MI325X โ†’ ~35 yes 194k โ€”
AMD Instinct MI300X 192GB โ†’ ~30.9 yes 82k ~$15,000

Estimate at Q4 (memory-bound). Click any option for its full per-hardware estimate and measured numbers.

FAQ

What Datacenter GPU hardware runs DeepSeek-V2 (MoE-236B)?โ–ถ

On GenAIList, 3 Datacenter GPU options can run DeepSeek-V2 (MoE-236B) at Q4 โ€” the fastest is the NVIDIA B200 at ~52.7 tok/s.

How fast is DeepSeek-V2 (MoE-236B) on Datacenter GPU hardware?โ–ถ

Estimated generation speed ranges from ~30.9 to ~52.7 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.