🔌
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 GLIDE?
Yes — here's how fast and up to what context, with real measured numbers.
GLIDE on the NVIDIA H200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1850k | 500.6-596.6 t/s | ~4.2-5 (slow) |
| Q8 | yes | 1903k | 1001.1-1193.1 t/s | ~8.3-9.9 (slow) |
| Q4 | yes | 1927k | 1787.8-2130.6 t/s | ~14.9-17.8 (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 GLIDE?▶
Yes. At Q4 it generates ~1787.8-2130.6 tok/s and fits up to 1927k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~14.9-17.8 tok/s.
How much context fits?▶
At Q4, up to about 1927k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.