// RUN ON DATACENTER GPU

Run Ankh_base on Datacenter GPU hardware

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

HardwareEst tok/sFits 8k?Max ctx~Price
NVIDIA B200 โ†’ ~16,795.4 yes 2666k โ€”
AMD Instinct MI325X โ†’ ~11,148.6 yes 3565k โ€”
NVIDIA H200 โ†’ ~10,077.2 yes 1950k โ€”
AMD Instinct MI300X 192GB โ†’ ~9,848 yes 2666k ~$15,000
NVIDIA H100 SXM5 80GB โ†’ ~7,033.1 yes 1094k ~$30,000
Intel Gaudi 3 โ†’ ~6,428.6 yes 1768k โ€”
NVIDIA A100 SXM4 80GB โ†’ ~4,280.7 yes 1094k ~$15,000
NVIDIA H100 PCIe 80GB โ†’ ~4,198.8 yes 1094k ~$25,000
NVIDIA A100 PCIe 80GB โ†’ ~4,062.4 yes 1094k ~$12,000
NVIDIA RTX PRO 6000 Blackwell โ†’ ~3,762.2 yes 1318k ~$8,500
NVIDIA RTX 6000 Ada 48GB โ†’ ~2,015.4 yes 645k ~$6,800
NVIDIA L40S 48GB โ†’ ~1,813.9 yes 645k ~$10,000
AMD Radeon Pro W7900 48GB โ†’ ~1,605.4 yes 645k ~$3,999

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

FAQ

What Datacenter GPU hardware runs Ankh_base?โ–ถ

On GenAIList, 13 Datacenter GPU options can run Ankh_base at Q4 โ€” the fastest is the NVIDIA B200 at ~16,795.4 tok/s.

How fast is Ankh_base on Datacenter GPU hardware?โ–ถ

Estimated generation speed ranges from ~1,605.4 to ~16,795.4 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.