// RUN โ€” FITS

Can the NVIDIA H200 run ether0?

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

ether0 on the NVIDIA H200

QuantFits?Max contextSpeedBeyond context
FP16 yes 306k 73-87 t/s ~0.6-0.7 (slow)
Q8 yes 398k 146-174 t/s ~1.2-1.5 (slow)
Q4 yes 438k 260.7-310.7 t/s ~2.2-2.6 (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 NVIDIA H200 run ether0?โ–ถ

Yes. At Q4 it generates ~260.7-310.7 tok/s and fits up to 438k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~2.2-2.6 tok/s.

How much context fits?โ–ถ

At Q4, up to about 438k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.