🔌
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 ProGen2-base?
Yes — here's how fast and up to what context, with real measured numbers.
ProGen2-base on the Instinct MI440X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 6018k | 8081.2-9877 t/s | ~16.5-20.2 (slow) |
| Q8 | yes | 6030k | 16162.3-19753.9 t/s | ~33-40.3 (slow) |
| Q4 | yes | 6035k | 28861.3-35274.9 t/s | ~58.9-72 (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 ProGen2-base?▶
Yes. At Q4 it generates ~28861.3-35274.9 tok/s and fits up to 6035k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~58.9-72 tok/s.
How much context fits?▶
At Q4, up to about 6035k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.