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 mBART-50?
Yes — here's how fast and up to what context, with real measured numbers.
mBART-50 on the NVIDIA H200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1938k | 2872.1-3423 t/s | ~23.9-28.5 (slow) |
| Q8 | yes | 1947k | 5744.3-6845.9 t/s | ~47.9-57 (slow) |
| Q4 | yes | 1951k | 10257.6-12224.8 t/s | ~85.5-101.9 (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 mBART-50?▶
Yes. At Q4 it generates ~10257.6-12224.8 tok/s and fits up to 1951k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~85.5-101.9 tok/s.
How much context fits?▶
At Q4, up to about 1951k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.