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 OPT-125M (finetuned)?
Yes — here's how fast and up to what context, with real measured numbers.
OPT-125M (finetuned) on the NVIDIA H200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1953k | 14016-16704 t/s | ~116.8-139.2 (slow) |
| Q8 | yes | 1955k | 28032-33408 t/s | ~233.6-278.4 (slow) |
| Q4 | yes | 1955k | 50057.1-59657.1 t/s | ~417.1-497.1 (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 OPT-125M (finetuned)?▶
Yes. At Q4 it generates ~50057.1-59657.1 tok/s and fits up to 1955k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~417.1-497.1 tok/s.
How much context fits?▶
At Q4, up to about 1955k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.