community pool / model answer

Qwen3.6-27b-ROCmFP4-CIRU-CHAOS-SPEED

chat · jcbtc/Qwen3.6-27b-ROCmFP4-CIRU-CHAOS-SPEED

92.3 tok/s · model median · 2 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
Ryzen AI Max 395 128GB4-bit132.3 tok/sreported105- GB2,048llama.cpp
Ryzen AI Max 395 128GB16-bit52.2 tok/sreported339- 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.