🔌
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 WizardCoder-15.5B?
Yes — here's how fast and up to what context, with real measured numbers.
WizardCoder-15.5B on the Instinct MI430X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1392k | 473.5-578.7 t/s | ~0.8-1 (slow) |
| Q8 | yes | 1451k | 947-1157.5 t/s | ~1.6-2 (slow) |
| Q4 | yes | 1477k | 1691.1-2066.9 t/s | ~2.9-3.5 (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 WizardCoder-15.5B?▶
Yes. At Q4 it generates ~1691.1-2066.9 tok/s and fits up to 1477k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~2.9-3.5 tok/s.
How much context fits?▶
At Q4, up to about 1477k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.