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 ADM?
Yes — here's how fast and up to what context, with real measured numbers.
ADM on the NVIDIA H200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1939k | 3134.2-3735.2 t/s | ~26.1-31.1 (slow) |
| Q8 | yes | 1948k | 6268.3-7470.5 t/s | ~52.2-62.3 (slow) |
| Q4 | yes | 1952k | 11193.5-13340.1 t/s | ~93.3-111.2 (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 ADM?▶
Yes. At Q4 it generates ~11193.5-13340.1 tok/s and fits up to 1952k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~93.3-111.2 tok/s.
How much context fits?▶
At Q4, up to about 1952k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.