// RUN โ€” FITS

Can the AMD Radeon Pro W7900 48GB run nekomata-14b?

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

nekomata-14b on the AMD Radeon Pro W7900 48GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 87k 19.2-23.4 t/s ~0.9-1.1 (slow)
Q8 yes 174k 38.3-46.9 t/s ~1.8-2.2 (slow)
Q4 yes 212k 68.5-83.7 t/s ~3.2-3.9 (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 AMD Radeon Pro W7900 48GB run nekomata-14b?โ–ถ

Yes. At Q4 it generates ~68.5-83.7 tok/s and fits up to 212k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~3.2-3.9 tok/s.

How much context fits?โ–ถ

At Q4, up to about 212k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.