🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// RUN ON DATACENTER GPU
Run InternVL2-Llama3-76B on Datacenter GPU hardware
10 options ranked by estimated speed at Q4 / 8k context.
| Hardware | Est tok/s | Fits 8k? | Max ctx | ~Price |
|---|---|---|---|---|
| NVIDIA B200 → | ~163.5 | yes | 405k | — |
| AMD Instinct MI325X → | ~108.6 | yes | 584k | — |
| NVIDIA H200 → | ~98.1 | yes | 261k | — |
| AMD Instinct MI300X 192GB → | ~95.9 | yes | 405k | ~$15,000 |
| NVIDIA H100 SXM5 80GB → | ~68.5 | yes | 90k | ~$30,000 |
| Intel Gaudi 3 → | ~62.6 | yes | 225k | — |
| NVIDIA A100 SXM4 80GB → | ~41.7 | yes | 90k | ~$15,000 |
| NVIDIA H100 PCIe 80GB → | ~40.9 | yes | 90k | ~$25,000 |
| NVIDIA A100 PCIe 80GB → | ~39.6 | yes | 90k | ~$12,000 |
| NVIDIA RTX PRO 6000 Blackwell → | ~36.6 | yes | 135k | ~$8,500 |
Estimate at Q4 (memory-bound). Click any option for its full per-hardware estimate and measured numbers.
FAQ
What Datacenter GPU hardware runs InternVL2-Llama3-76B?▶
On GenAIList, 10 Datacenter GPU options can run InternVL2-Llama3-76B at Q4 — the fastest is the NVIDIA B200 at ~163.5 tok/s.
How fast is InternVL2-Llama3-76B on Datacenter GPU hardware?▶
Estimated generation speed ranges from ~36.6 to ~163.5 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.