🔌
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 Gemma 3 QAT 12B?
Yes — here's how fast and up to what context, with real measured numbers.
Gemma 3 QAT 12B on the NVIDIA H200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 636k | 146-174 t/s | ~1.2-1.5 (slow) |
| Q8 | yes | 709k | 292-348 t/s | ~2.4-2.9 (slow) |
| Q4 | yes | 742k | 521.4-621.4 t/s | ~4.3-5.2 (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 Gemma 3 QAT 12B?▶
Yes. At Q4 it generates ~521.4-621.4 tok/s and fits up to 742k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~4.3-5.2 tok/s.
How much context fits?▶
At Q4, up to about 742k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.