// RUN โ€” FITS

Can the Intel Arc Pro B70 run DeepSeek Coder 6.7B?

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

DeepSeek Coder 6.7B on the Intel Arc Pro B70

QuantFits?Max contextSpeedBeyond context
FP16 yes 111k 26.3-32.7 t/s ~1.7-2.1 (slow)
Q8 yes 162k 52.6-65.3 t/s ~3.5-4.3 (slow)
Q4 yes 185k 94-116.7 t/s ~6.2-7.7 (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 Pro B70 run DeepSeek Coder 6.7B?โ–ถ

Yes. At Q4 it generates ~94-116.7 tok/s and fits up to 185k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~6.2-7.7 tok/s.

How much context fits?โ–ถ

At Q4, up to about 185k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.