🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// RUN — FITS
Can the NVIDIA H200 run ESM3-open-small?
Yes — here's how fast and up to what context, with real measured numbers.
ESM3-open-small on the NVIDIA H200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1914k | 1251.4-1491.4 t/s | ~10.4-12.4 (slow) |
| Q8 | yes | 1935k | 2502.9-2982.9 t/s | ~20.9-24.9 (slow) |
| Q4 | yes | 1945k | 4469.4-5326.5 t/s | ~37.2-44.4 (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 ESM3-open-small?▶
Yes. At Q4 it generates ~4469.4-5326.5 tok/s and fits up to 1945k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~37.2-44.4 tok/s.
How much context fits?▶
At Q4, up to about 1945k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.