// RUN โ€” FITS

Can the NVIDIA A100 SXM4 80GB run Tri-21B?

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

Tri-21B on the NVIDIA A100 SXM4 80GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 117k 35.9-42.8 t/s ~0.7-0.8 (slow)
Q8 yes 196k 71.8-85.6 t/s ~1.4-1.7 (slow)
Q4 yes 231k 128.2-152.8 t/s ~2.5-3 (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 A100 SXM4 80GB run Tri-21B?โ–ถ

Yes. At Q4 it generates ~128.2-152.8 tok/s and fits up to 231k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~2.5-3 tok/s.

How much context fits?โ–ถ

At Q4, up to about 231k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.