DefiledAI

WEEKLY DIGEST

New model drops, recent articles, tutorial updates, and backend news. Subscribe via RSS.

Week of May 31, 2026LATEST
New Model Drops
4 this week
Llama 3.1 70B Abliterated v3ABLITERATED
by failspy
Updated quality retention on reasoning chains.
HF ↗
Qwen 2.5 72B Uncensored GGUFUNCENSORED
by bartowski
Full quant pack Q2_K through Q8_0.
HF ↗
Mistral Nemo 12B AbliteratedABLITERATED
by bartowski
128K context retained.
HF ↗
DeepSeek R1 8B AbliteratedABLITERATED
by Community
6GB VRAM minimum.
HF ↗
Recent Articles
New Tutorials
Backend & Tool Updates
ExLlamaV2 v0.2.4 — ~12% throughput improvement on Q4_K_M for Ada GPUs
llama.cpp adds experimental Q4_K_XS format — smaller than Q4_K_S at similar quality
Community finds secondary refusal vectors in Llama 3.1 — improved abliteration script posted
ROCm 6.2 released — closes AMD/CUDA inference gap on RX 7000 series