community-verified · measured pool data

Can the RX 7900 XTX 24GB run Qwopus3.6-27B-v2-MTP-GGUF?

Yes — community-measured at 67.2 tok/s (7 runs at 6-bit).

Verified single-stream runs on the RX 7900 XTX 24GB from the localmaxxing public pool. Every number on this page is measured — nothing here is estimated.

Quantization	Median tok/s	TTFT (ms)	Peak VRAM	Max context tested	Engines
4-bit	40.7	1329	22.4 GB	8,192	llama.cpp
6-bit	67.2	—	22 GB	262,144	llama.cpp

Go deeper

I have a goal — find models that fit my use case → I have hardware — browse everything my rig can run → All machine × model answer pages →