New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Can the Instinct MI430X run OpenELM-1.1B?
Yes — here's how fast and up to what context, with real measured numbers.
OpenELM-1.1B on the Instinct MI430X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 6009k | 6795.8-8306 t/s | ~11.7-14.3 (slow) |
| Q8 | yes | 6025k | 13591.7-16612 t/s | ~23.3-28.5 (slow) |
| Q4 | yes | 6032k | 24270.8-29664.4 t/s | ~41.7-50.9 (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-1.1B?▶
Yes. At Q4 it generates ~24270.8-29664.4 tok/s and fits up to 6032k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~41.7-50.9 tok/s.
How much context fits?▶
At Q4, up to about 6032k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.