Remove the charts built from the old merge measurements

Rewrite the card: single-pass measurements with error bars, provenance evidence, changelog

Chart: top-token divergence, old merge vs corrected merge

Chart: measured quality cost per level

Chart: sizes against a 12 GB budget

Banner: new weights published

Fresh importance matrix computed on the corrected V3 Q8_0 (calibration_datav3, 129 chunks)

Rebuild IQ2_S from the corrected V3 Q8_0 (fixed abliteration merge) + upstream chat template

Rebuild IQ2_M from the corrected V3 Q8_0 (fixed abliteration merge) + upstream chat template

Rebuild IQ2_XXS from the corrected V3 Q8_0 (fixed abliteration merge) + upstream chat template

Rebuild IQ3_XXS from the corrected V3 Q8_0 (fixed abliteration merge) + upstream chat template

Put notice banner at the top of the card

Add breaking-news notice banner

Add rebuild-in-progress notice (upstream GGUF conversion fix) + embed benchmark charts

add benchmark chart assets/bench-quality-vs-speed.png

add benchmark chart assets/bench-vram-12gb.png

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload imatrix.gguf with huggingface_hub

Upload Qwen3.8-27B-OBLITERATED.IQ3_XXS.gguf with huggingface_hub

Upload Qwen3.8-27B-OBLITERATED.IQ2_XXS.gguf with huggingface_hub

Upload Qwen3.8-27B-OBLITERATED.IQ2_S.gguf with huggingface_hub

Upload Qwen3.8-27B-OBLITERATED.IQ2_M.gguf with huggingface_hub

initial commit