🔌
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 Qwen2.5-3B on Datacenter GPU hardware
13 options ranked by estimated speed at Q4 / 8k context.
| Hardware | Est tok/s | Fits 8k? | Max ctx | ~Price |
|---|---|---|---|---|
| NVIDIA B200 → | ~4,022.2 | yes | 2646k | — |
| AMD Instinct MI325X → | ~2,669.9 | yes | 3544k | — |
| NVIDIA H200 → | ~2,413.3 | yes | 1930k | — |
| AMD Instinct MI300X 192GB → | ~2,358.4 | yes | 2646k | ~$15,000 |
| NVIDIA H100 SXM5 80GB → | ~1,684.3 | yes | 1074k | ~$30,000 |
| Intel Gaudi 3 → | ~1,539.5 | yes | 1748k | — |
| NVIDIA A100 SXM4 80GB → | ~1,025.2 | yes | 1074k | ~$15,000 |
| NVIDIA H100 PCIe 80GB → | ~1,005.5 | yes | 1074k | ~$25,000 |
| NVIDIA A100 PCIe 80GB → | ~972.9 | yes | 1074k | ~$12,000 |
| NVIDIA RTX PRO 6000 Blackwell → | ~901 | yes | 1298k | ~$8,500 |
| NVIDIA RTX 6000 Ada 48GB → | ~482.7 | yes | 625k | ~$6,800 |
| NVIDIA L40S 48GB → | ~434.4 | yes | 625k | ~$10,000 |
| AMD Radeon Pro W7900 48GB → | ~384.5 | yes | 625k | ~$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 Qwen2.5-3B?▶
On GenAIList, 13 Datacenter GPU options can run Qwen2.5-3B at Q4 — the fastest is the NVIDIA B200 at ~4,022.2 tok/s.
How fast is Qwen2.5-3B on Datacenter GPU hardware?▶
Estimated generation speed ranges from ~384.5 to ~4,022.2 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.