// RUN โ€” FITS

Can the Intel Arc B580 12GB run AWD-LSTM-DOC (fin) (23M)?

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

AWD-LSTM-DOC (fin) (23M) on the Intel Arc B580 12GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 145k 5749.6-7137.4 t/s ~504.3-626.1 (slow)
Q8 yes 145k 11499.1-14274.8 t/s ~1008.7-1252.2 (slow)
Q4 yes 145k 20534.2-25490.7 t/s ~1801.2-2236 (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 B580 12GB run AWD-LSTM-DOC (fin) (23M)?โ–ถ

Yes. At Q4 it generates ~20534.2-25490.7 tok/s and fits up to 145k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1801.2-2236 tok/s.

How much context fits?โ–ถ

At Q4, up to about 145k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.