🔌
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 TinyLlama-1.1B (3T token checkpoint) 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 → | ~11,298.7 | yes | 2663k | — |
| AMD Instinct MI325X → | ~7,500 | yes | 3561k | — |
| NVIDIA H200 → | ~6,779.2 | yes | 1947k | — |
| AMD Instinct MI300X 192GB → | ~6,625 | yes | 2663k | ~$15,000 |
| NVIDIA H100 SXM5 80GB → | ~4,731.3 | yes | 1091k | ~$30,000 |
| Intel Gaudi 3 → | ~4,324.7 | yes | 1765k | — |
| NVIDIA A100 SXM4 80GB → | ~2,879.8 | yes | 1091k | ~$15,000 |
| NVIDIA H100 PCIe 80GB → | ~2,824.7 | yes | 1091k | ~$25,000 |
| NVIDIA A100 PCIe 80GB → | ~2,732.9 | yes | 1091k | ~$12,000 |
| NVIDIA RTX PRO 6000 Blackwell → | ~2,530.9 | yes | 1315k | ~$8,500 |
| NVIDIA RTX 6000 Ada 48GB → | ~1,355.8 | yes | 642k | ~$6,800 |
| NVIDIA L40S 48GB → | ~1,220.3 | yes | 642k | ~$10,000 |
| AMD Radeon Pro W7900 48GB → | ~1,080 | yes | 642k | ~$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 TinyLlama-1.1B (3T token checkpoint)?▶
On GenAIList, 13 Datacenter GPU options can run TinyLlama-1.1B (3T token checkpoint) at Q4 — the fastest is the NVIDIA B200 at ~11,298.7 tok/s.
How fast is TinyLlama-1.1B (3T token checkpoint) on Datacenter GPU hardware?▶
Estimated generation speed ranges from ~1,080 to ~11,298.7 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.