// RUN โ€” FITS

Can the Intel Arc A770 16GB run Tranception?

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

Tranception on the Intel Arc A770 16GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 180k 232-288 t/s ~16.6-20.6 (slow)
Q8 yes 191k 464-576 t/s ~33.1-41.1 (slow)
Q4 yes 196k 828.6-1028.6 t/s ~59.2-73.5 (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 Tranception?โ–ถ

Yes. At Q4 it generates ~828.6-1028.6 tok/s and fits up to 196k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~59.2-73.5 tok/s.

How much context fits?โ–ถ

At Q4, up to about 196k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.