🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// RUN — FITS
Can the NVIDIA H200 run T5-3B?
Yes — here's how fast and up to what context, with real measured numbers.
T5-3B on the NVIDIA H200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1871k | 625.7-745.7 t/s | ~5.2-6.2 (slow) |
| Q8 | yes | 1914k | 1251.4-1491.4 t/s | ~10.4-12.4 (slow) |
| Q4 | yes | 1933k | 2234.7-2663.3 t/s | ~18.6-22.2 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to system RAM offload (depends on your system RAM) and speed drops to the "beyond" figure.
FAQ
Can the NVIDIA H200 run T5-3B?▶
Yes. At Q4 it generates ~2234.7-2663.3 tok/s and fits up to 1933k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~18.6-22.2 tok/s.
How much context fits?▶
At Q4, up to about 1933k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.