community pool / model answer

Qwen3.8-Flash-Next

chat · Qwen/Qwen3.8-Flash-Next

14.8 tok/s · model median · 3 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
M3 Ultra 512GB4-bit14 tok/sreported2,053- GB2,048mlx
Radeon AI Pro R9700 32GB ×33-bit28.1 tok/sreported1,208- GB829llama.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.