🔌
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 MI430X run OpenELM-450M?
Yes — here's how fast and up to what context, with real measured numbers.
OpenELM-450M on the Instinct MI430X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 6028k | 16310-19934.4 t/s | ~28-34.2 (slow) |
| Q8 | yes | 6035k | 32620-39868.9 t/s | ~56-68.4 (slow) |
| Q4 | yes | 6038k | 58250-71194.4 t/s | ~100-122.2 (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 MI430X run OpenELM-450M?▶
Yes. At Q4 it generates ~58250-71194.4 tok/s and fits up to 6038k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~100-122.2 tok/s.
How much context fits?▶
At Q4, up to about 6038k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.