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 ESM2-8M?
Yes — here's how fast and up to what context, with real measured numbers.
ESM2-8M on the Instinct MI430X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 6041k | 917437.5-1121312.5 t/s | ~1575-1925 (slow) |
| Q8 | yes | 6041k | 1834875-2242625 t/s | ~3150-3850 (slow) |
| Q4 | yes | 6041k | 3276562.5-4004687.5 t/s | ~5625-6875 (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 ESM2-8M?▶
Yes. At Q4 it generates ~3276562.5-4004687.5 tok/s and fits up to 6041k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~5625-6875 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.