🔌
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 CodeT5-large?
Yes — here's how fast and up to what context, with real measured numbers.
CodeT5-large on the NVIDIA H200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1933k | 2275.3-2711.7 t/s | ~19-22.6 (slow) |
| Q8 | yes | 1945k | 4550.6-5423.4 t/s | ~37.9-45.2 (slow) |
| Q4 | yes | 1950k | 8126.2-9684.6 t/s | ~67.7-80.7 (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 CodeT5-large?▶
Yes. At Q4 it generates ~8126.2-9684.6 tok/s and fits up to 1950k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~67.7-80.7 tok/s.
How much context fits?▶
At Q4, up to about 1950k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.