// RUN โ€” FITS

Can the AMD Radeon RX 7800 XT run TRIMELMext (7M)?

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

TRIMELMext (7M) on the AMD Radeon RX 7800 XT

QuantFits?Max contextSpeedBeyond context
FP16 yes 202k 28080-34320 t/s ~1800-2200 (slow)
Q8 yes 202k 56160-68640 t/s ~3600-4400 (slow)
Q4 yes 202k 100285.7-122571.4 t/s ~6428.6-7857.1 (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 RX 7800 XT run TRIMELMext (7M)?โ–ถ

Yes. At Q4 it generates ~100285.7-122571.4 tok/s and fits up to 202k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~6428.6-7857.1 tok/s.

How much context fits?โ–ถ

At Q4, up to about 202k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.