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 Gemma 3 270M?
Yes — here's how fast and up to what context, with real measured numbers.
Gemma 3 270M on the NVIDIA H200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1948k | 6488.9-7733.3 t/s | ~54.1-64.4 (slow) |
| Q8 | yes | 1952k | 12977.8-15466.7 t/s | ~108.1-128.9 (slow) |
| Q4 | yes | 1954k | 23174.6-27619 t/s | ~193.1-230.2 (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 270M?▶
Yes. At Q4 it generates ~23174.6-27619 tok/s and fits up to 1954k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~193.1-230.2 tok/s.
How much context fits?▶
At Q4, up to about 1954k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.