// RUN โ€” FITS

Can the Intel Arc Pro B70 run DeciCoder-6B?

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

DeciCoder-6B on the Intel Arc Pro B70

QuantFits?Max contextSpeedBeyond context
FP16 yes 122k 29.4-36.5 t/s ~1.9-2.4 (slow)
Q8 yes 167k 58.8-73 t/s ~3.9-4.8 (slow)
Q4 yes 188k 105-130.3 t/s ~6.9-8.6 (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 Pro B70 run DeciCoder-6B?โ–ถ

Yes. At Q4 it generates ~105-130.3 tok/s and fits up to 188k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~6.9-8.6 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.