community pool / model answer

Qwen3.5-27B

chat · unsloth/Qwen3.5-27B

29 tok/s · model median · 5 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
Radeon AI Pro R9700 32GB4-bit29.1 tok/smeasured74- GB2,048llama.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.