🔌
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 OpenELM-1.1B?
Yes — here's how fast and up to what context, with real measured numbers.
OpenELM-1.1B on the NVIDIA H200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1924k | 1622.2-1933.3 t/s | ~13.5-16.1 (slow) |
| Q8 | yes | 1940k | 3244.4-3866.7 t/s | ~27-32.2 (slow) |
| Q4 | yes | 1947k | 5793.7-6904.8 t/s | ~48.3-57.5 (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 OpenELM-1.1B?▶
Yes. At Q4 it generates ~5793.7-6904.8 tok/s and fits up to 1947k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~48.3-57.5 tok/s.
How much context fits?▶
At Q4, up to about 1947k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.