🔌
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 SantaCoder?
Yes — here's how fast and up to what context, with real measured numbers.
SantaCoder on the Instinct MI430X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 6008k | 6672.3-8155 t/s | ~11.5-14 (slow) |
| Q8 | yes | 6025k | 13344.5-16310 t/s | ~22.9-28 (slow) |
| Q4 | yes | 6032k | 23829.5-29125 t/s | ~40.9-50 (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 SantaCoder?▶
Yes. At Q4 it generates ~23829.5-29125 tok/s and fits up to 6032k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~40.9-50 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.