// RUN โ€” FITS

Can the Intel Arc A770 16GB run Refact-1.6B?

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

Refact-1.6B on the Intel Arc A770 16GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 153k 101.5-126 t/s ~7.3-9 (slow)
Q8 yes 177k 203-252 t/s ~14.5-18 (slow)
Q4 yes 188k 362.5-450 t/s ~25.9-32.1 (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 Refact-1.6B?โ–ถ

Yes. At Q4 it generates ~362.5-450 tok/s and fits up to 188k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~25.9-32.1 tok/s.

How much context fits?โ–ถ

At Q4, up to about 188k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.