New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Can the NVIDIA H200 run Pythia-410m?
Yes — here's how fast and up to what context, with real measured numbers.
Pythia-410m on the NVIDIA H200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1944k | 4273.2-5092.7 t/s | ~35.6-42.4 (slow) |
| Q8 | yes | 1950k | 8546.3-10185.4 t/s | ~71.2-84.9 (slow) |
| Q4 | yes | 1953k | 15261.3-18188.2 t/s | ~127.2-151.6 (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 Pythia-410m?▶
Yes. At Q4 it generates ~15261.3-18188.2 tok/s and fits up to 1953k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~127.2-151.6 tok/s.
How much context fits?▶
At Q4, up to about 1953k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.