// RUN โ€” FITS

Can the NVIDIA RTX PRO 6000 Blackwell run Gemma 3 QAT 27B?

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

Gemma 3 QAT 27B on the NVIDIA RTX PRO 6000 Blackwell

QuantFits?Max contextSpeedBeyond context
FP16 yes 125k 24.2-28.9 t/s ~0.5-0.6 (slow)
Q8 yes 228k 48.5-57.7 t/s ~1.1-1.3 (slow)
Q4 yes 274k 86.5-103.1 t/s ~1.9-2.3 (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 NVIDIA RTX PRO 6000 Blackwell run Gemma 3 QAT 27B?โ–ถ

Yes. At Q4 it generates ~86.5-103.1 tok/s and fits up to 274k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1.9-2.3 tok/s.

How much context fits?โ–ถ

At Q4, up to about 274k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.