🔌
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 Instinct MI440X run Prithvi-100M?
Yes — here's how fast and up to what context, with real measured numbers.
Prithvi-100M on the Instinct MI440X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 6039k | 61740-75460 t/s | ~126-154 (slow) |
| Q8 | yes | 6040k | 123480-150920 t/s | ~252-308 (slow) |
| Q4 | yes | 6041k | 220500-269500 t/s | ~450-550 (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 Instinct MI440X run Prithvi-100M?▶
Yes. At Q4 it generates ~220500-269500 tok/s and fits up to 6041k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~450-550 tok/s.
How much context fits?▶
At Q4, up to about 6041k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.