community pool / model answer

Qwopus3.6-27B-v2-MTP-GGUF

chat · Jackrong/Qwopus3.6-27B-v2-MTP-GGUF

56.1 tok/s · model median · 12 runs in the model record.

Reference rig	Quantization	Median result	Basis	TTFT (ms)	Peak VRAM	Max context	Engines
Radeon AI Pro R9700 32GB	6-bit	53.9 tok/s	measured	-	30.3 GB	262,144	llama.cpp
RX 7900 XTX 24GB	4-bit	40.7 tok/s	reported	1,329	22.4 GB	8,192	llama.cpp
RX 7900 XTX 24GB	6-bit	67.2 tok/s	measured	-	22 GB	262,144	llama.cpp

Context tested

The table above is the tested context for each exact rig and quantization cell. Empty fields remain empty rather than being filled with an estimate.