// RUN — FITS

Can the AMD Radeon RX 7900 XT run Pharia-1-LLM-7B?

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

Pharia-1-LLM-7B on the AMD Radeon RX 7900 XT

QuantFits?Max contextSpeedBeyond context
FP16 yes 21k 35.8-43.7 t/s ~1.8-2.2 (slow)
Q8 yes 75k 71.6-87.5 t/s ~3.6-4.4 (slow)
Q4 yes 99k 127.8-156.2 t/s ~6.4-7.8 (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.

→ All models on the AMD Radeon RX 7900 XT → Pharia-1-LLM-7B specs → Other hardware

FAQ

Can the AMD Radeon RX 7900 XT run Pharia-1-LLM-7B?▶

Yes. At Q4 it generates ~127.8-156.2 tok/s and fits up to 99k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~6.4-7.8 tok/s.

How much context fits?▶

At Q4, up to about 99k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.