🔌
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 MI440X run Yi-1.5-9B?
Yes — here's how fast and up to what context, with real measured numbers.
Yi-1.5-9B on the Instinct MI440X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2886k | 699.2-854.6 t/s | ~1.4-1.7 (slow) |
| Q8 | yes | 2953k | 1398.4-1709.2 t/s | ~2.9-3.5 (slow) |
| Q4 | yes | 2983k | 2497.2-3052.1 t/s | ~5.1-6.2 (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 MI440X run Yi-1.5-9B?▶
Yes. At Q4 it generates ~2497.2-3052.1 tok/s and fits up to 2983k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~5.1-6.2 tok/s.
How much context fits?▶
At Q4, up to about 2983k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.