🔌
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 Pythia-6.9b?
Yes — here's how fast and up to what context, with real measured numbers.
Pythia-6.9b on the Instinct MI430X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2915k | 1063.7-1300.1 t/s | ~1.8-2.2 (slow) |
| Q8 | yes | 2968k | 2127.4-2600.1 t/s | ~3.7-4.5 (slow) |
| Q4 | yes | 2991k | 3798.9-4643.1 t/s | ~6.5-8 (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 Pythia-6.9b?▶
Yes. At Q4 it generates ~3798.9-4643.1 tok/s and fits up to 2991k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~6.5-8 tok/s.
How much context fits?▶
At Q4, up to about 2991k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.