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 Retrieval-Augmented Generator?
Yes — here's how fast and up to what context, with real measured numbers.
Retrieval-Augmented Generator on the NVIDIA H200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1937k | 2798.7-3335.5 t/s | ~23.3-27.8 (slow) |
| Q8 | yes | 1947k | 5597.4-6670.9 t/s | ~46.6-55.6 (slow) |
| Q4 | yes | 1951k | 9995.4-11912.4 t/s | ~83.3-99.3 (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 Retrieval-Augmented Generator?▶
Yes. At Q4 it generates ~9995.4-11912.4 tok/s and fits up to 1951k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~83.3-99.3 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.