🔌
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 ANITA-NEXT 24B Vision?
Yes — here's how fast and up to what context, with real measured numbers.
ANITA-NEXT 24B Vision on the Instinct MI430X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1327k | 305.8-373.8 t/s | ~0.5-0.6 (slow) |
| Q8 | yes | 1419k | 611.6-747.5 t/s | ~1.1-1.3 (slow) |
| Q4 | yes | 1459k | 1092.2-1334.9 t/s | ~1.9-2.3 (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 ANITA-NEXT 24B Vision?▶
Yes. At Q4 it generates ~1092.2-1334.9 tok/s and fits up to 1459k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1.9-2.3 tok/s.
How much context fits?▶
At Q4, up to about 1459k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.