// RUN โ€” FITS

Can the Intel Arc A770 16GB run Unified-IO (XL)?

Yes โ€” here's how fast and up to what context, with real measured numbers.

Unified-IO (XL) on the Intel Arc A770 16GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 112k 55.5-68.9 t/s ~4-4.9 (slow)
Q8 yes 157k 111-137.8 t/s ~7.9-9.8 (slow)
Q4 yes 177k 198.3-246.2 t/s ~14.2-17.6 (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 Intel Arc A770 16GB run Unified-IO (XL)?โ–ถ

Yes. At Q4 it generates ~198.3-246.2 tok/s and fits up to 177k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~14.2-17.6 tok/s.

How much context fits?โ–ถ

At Q4, up to about 177k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.