#uncensored

0 stories this week · 2 this month · 10 in 6 months · mostly AI

Stories per day · 30 days

10 stories, newest first · one card per story

AtomicChat releases 763B DeepSeek-V4.1-Flash-1017 uncensored GGUF quantized for single 12GB GPU with Strata.

AtomicChat reports harmful-prompt refusals fell from 61.7% to 0% with MMLU unchanged at 41.0%.

AtomicChat published abliterated GGUF weights of the Qwen-Image 2.1 Turbo text encoder, sharply cutting chat refusals.

SC117 published abliterated GGUF quants of Qwen3.8-Flash-Next that swap 144 tensors while keeping GSQ-RCO scales.

15 min readqwen gguf

Infatoshi published a 3.0 bpw EXL3 quant of uncensored GLM-5.3, a 753B MoE now trending on Hugging Face.

OrcaSAQ-2-Cyber-27B-Uncensored GGUF, a 27B text model, is trending on Hugging Face.

An uncensored GGUF version of Qwen-Image-2.1 for local image generation is trending, featuring no content filters and optimized for ComfyUI.

Hugging Face user dealignai published an uncensored FP8-quantized variant of DeepSeek v4.1 Flash, drawing moderate Hacker News attention.

DavidAU releases Qwen3.8-27B-TWIN-TURBO, an uncensored GGUF fine-tune claiming sharply reduced thinking tokens and self-reported benchmark gains.

A new Qwen3.8-27B GGUF fine-tune claims ARC-C 735 at 8-bit with thinking tokens cut 2x-10x versus the base model.

Stories tagged #uncensored