community pool / model answer

Qwen3.5-9B

chat · unsloth/Qwen3.5-9B

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
Ryzen AI Max 395 64GB4-bit38.1 tok/sreported1,7125.7 GB8,192llama.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.