🔌
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 EmbeddingGemma 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 → | ~40,352.5 | yes | 2670k | — |
| AMD Instinct MI325X → | ~26,785.7 | yes | 3568k | — |
| NVIDIA H200 → | ~24,211.5 | yes | 1954k | — |
| AMD Instinct MI300X 192GB → | ~23,660.7 | yes | 2670k | ~$15,000 |
| NVIDIA H100 SXM5 80GB → | ~16,897.6 | yes | 1098k | ~$30,000 |
| Intel Gaudi 3 → | ~15,445.3 | yes | 1771k | — |
| NVIDIA A100 SXM4 80GB → | ~10,284.8 | yes | 1098k | ~$15,000 |
| NVIDIA H100 PCIe 80GB → | ~10,088.1 | yes | 1098k | ~$25,000 |
| NVIDIA A100 PCIe 80GB → | ~9,760.3 | yes | 1098k | ~$12,000 |
| NVIDIA RTX PRO 6000 Blackwell → | ~9,039 | yes | 1322k | ~$8,500 |
| NVIDIA RTX 6000 Ada 48GB → | ~4,842.3 | yes | 648k | ~$6,800 |
| NVIDIA L40S 48GB → | ~4,358.1 | yes | 648k | ~$10,000 |
| AMD Radeon Pro W7900 48GB → | ~3,857.1 | yes | 648k | ~$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 EmbeddingGemma?▶
On GenAIList, 13 Datacenter GPU options can run EmbeddingGemma at Q4 — the fastest is the NVIDIA B200 at ~40,352.5 tok/s.
How fast is EmbeddingGemma on Datacenter GPU hardware?▶
Estimated generation speed ranges from ~3,857.1 to ~40,352.5 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.