spiritfather/MiniMax-M3-uncensored-GGUF

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Fill IQ2_S row (PPL 5.7374 +40.20%, KLD 0.4698) — ladder complete

Upload folder using huggingface_hub

Fill IQ3_S row (PPL 5.2967 +29.44%, KLD 0.3703)

Upload folder using huggingface_hub

README: fill Q4_K_M row (246 GiB, PPL 4.2198, +3.12%, KLD 0.0680)

Upload folder using huggingface_hub

README: fill Q5_K_M row (295 GiB, PPL 4.1219, +0.73%, KLD 0.0377)

Upload folder using huggingface_hub

README: fill IQ4_XS PPL/KLD (4.5772, +11.85%, KLD 0.1685 vs Q8_0)

README: link Q8_0 shards

Add Q8_0 shards (reference quant)

README: AesSedai-shape quant table (BPW, PPL-ratio col)

README: rich (CaliperBench) layout

Upload folder using huggingface_hub

Delete files test/imatrix.gguf with huggingface_hub

Upload README.md with huggingface_hub

Upload test/imatrix.gguf with huggingface_hub

Upload README.md with huggingface_hub

initial commit