inference-optimization/Qwen3-8B-DFlash-Gauss-FP8-W8A8
Text Generation • 1B • Updated • 8
Note Static FP8 W8A8; Gaussian calibration.
Note Static FP8 W8A8; PerfectBlend calibration.
Note NVFP4 W4A4; Gaussian calibration.
Note NVFP4 W4A4; PerfectBlend calibration.
Note FP8_DYNAMIC; data-free.