🔌
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 LLaDA2.2 Flash?
Yes — here's how fast and up to what context, with real measured numbers.
LLaDA2.2 Flash on the Instinct MI430X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 598k | 73.4-89.7 t/s | ~0.1-0.2 (slow) |
| Q8 | yes | 903k | 146.8-179.4 t/s | ~0.3-0.3 (slow) |
| Q4 | yes | 1037k | 262.1-320.4 t/s | ~0.5-0.6 (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 LLaDA2.2 Flash?▶
Yes. At Q4 it generates ~262.1-320.4 tok/s and fits up to 1037k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~0.5-0.6 tok/s.
How much context fits?▶
At Q4, up to about 1037k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.