🔌
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 VILA1.5-13B?
Yes — here's how fast and up to what context, with real measured numbers.
VILA1.5-13B on the NVIDIA H200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 618k | 129.8-154.7 t/s | ~1.1-1.3 (slow) |
| Q8 | yes | 700k | 259.7-309.5 t/s | ~2.2-2.6 (slow) |
| Q4 | yes | 736k | 463.7-552.6 t/s | ~3.9-4.6 (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 VILA1.5-13B?▶
Yes. At Q4 it generates ~463.7-552.6 tok/s and fits up to 736k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~3.9-4.6 tok/s.
How much context fits?▶
At Q4, up to about 736k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.