// RUN โ€” FITS

Can the Intel Arc A770 16GB run SeaLLM-7B-v2?

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

SeaLLM-7B-v2 on the Intel Arc A770 16GB

QuantFits?Max contextSpeedBeyond context
FP16 no โ€” โ€” โ€”
Q8 yes 45k 44-54.6 t/s ~3.1-3.9 (slow)
Q4 yes 69k 78.6-97.6 t/s ~5.6-7 (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 SeaLLM-7B-v2?โ–ถ

Yes. At Q4 it generates ~78.6-97.6 tok/s and fits up to 69k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~5.6-7 tok/s.

How much context fits?โ–ถ

At Q4, up to about 69k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.