🔌
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 SEA-LION V3 Gemma2 9B?
Yes — here's how fast and up to what context, with real measured numbers.
SEA-LION V3 Gemma2 9B on the NVIDIA H200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 841k | 194.7-232 t/s | ~1.6-1.9 (slow) |
| Q8 | yes | 910k | 389.3-464 t/s | ~3.2-3.9 (slow) |
| Q4 | yes | 940k | 695.2-828.6 t/s | ~5.8-6.9 (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 SEA-LION V3 Gemma2 9B?▶
Yes. At Q4 it generates ~695.2-828.6 tok/s and fits up to 940k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~5.8-6.9 tok/s.
How much context fits?▶
At Q4, up to about 940k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.