List your company

Quantization Robustness Evaluation on (Wikitext, C4, HellaSwag, MMLU, Arc-C, MATH500, GSM8K) Aggregate

-0.29Accuracy Loss Delta (%)HiF8
-0.42760.50121.432.3588Feb 13, 2026

Evaluation results

MethodLinks
HiF8Backbone=Qwen3-8B, WA Precision=W8A8, QKV Quantization=Q16KV82026.02-0.29
MXFP8Backbone=Qwen3-8B, WA Precision=W8A8, QKV Quantization=QKV82026.02-0.15
HiF8Backbone=openPangu-7B, WA Precision=W8A8, QKV Quantization=-2026.02-0.15
NVFP4Backbone=Qwen3-8B, WA Precision=W4A4, QKV Quantization=-2026.022.59
HiF4Backbone=Qwen3-8B, WA Precision=W4A4, QKV Quantization=Q16KV42026.023.15