🔌
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 Ovis1.6-Gemma2-9B?
Yes — here's how fast and up to what context, with real measured numbers.
Ovis1.6-Gemma2-9B on the NVIDIA H200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 658k | 171.8-204.7 t/s | ~1.4-1.7 (slow) |
| Q8 | yes | 720k | 343.5-409.4 t/s | ~2.9-3.4 (slow) |
| Q4 | yes | 748k | 613.4-731.1 t/s | ~5.1-6.1 (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 Ovis1.6-Gemma2-9B?▶
Yes. At Q4 it generates ~613.4-731.1 tok/s and fits up to 748k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~5.1-6.1 tok/s.
How much context fits?▶
At Q4, up to about 748k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.