// RUN — FITS

Can the Intel Arc A770 16GB run Baize-v2-13B (白泽)?

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

Baize-v2-13B (白泽) on the Intel Arc A770 16GB

QuantFits?Max contextSpeedBeyond context
FP16 no
Q8 yes 1k 25-31 t/s ~1.8-2.2 (slow)
Q4 yes 36k 44.6-55.4 t/s ~3.2-4 (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 Baize-v2-13B (白泽)?

Yes. At Q4 it generates ~44.6-55.4 tok/s and fits up to 36k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~3.2-4 tok/s.

How much context fits?

At Q4, up to about 36k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.