Dev Radar
Support
LiveUpdated 2026-09-19 18:06 UTC

Abliterlitics

Abliterlitics — Over 330 GPU-hours comparing 12 uncensored variants of Qwen3.8-27B across weight…

Abliterlitics is Over 330 GPU-hours comparing 12 uncensored variants of Qwen3.8-27B across weight forensics, heretic-exact KL divergence, a 13-task suite and judge-scored HarmBench at a 15,360-token thinking budget, all served in…. It is ranked #1059 on the Dev Radar, in Other, first seen 12 days ago and shared in 1 post (48.6k views).

Visit abliterlitics.dev

What people said about Abliterlitics on X

Someone independently benchmarked 8 different Qwen3.8-27B uncensored/abliterated models. We won. 🐳 Abliterlitics spent ~167 GPU-hours testing the variants across weight forensics, KL divergence, 13 capability benchmarks + 400 HarmBench behaviors. OrcaRouter Qwen3.8-27B-Uncensored: → #1 Judge ASR: 82.2% → Base model:…

@OrcaRouter, 12 days ago · 481 likes · see the post

Alternatives to Abliterlitics

Abliterlitics in numbers

FAQ

What is Abliterlitics?

Over 330 GPU-hours comparing 12 uncensored variants of Qwen3.8-27B across weight forensics, heretic-exact KL divergence, a 13-task suite and judge-scored HarmBench at a 15,360-token thinking budget, all served in… It was first shared on X 12 days ago and is ranked #1059 on the Dev Radar.

Is Abliterlitics free?

Pricing is not stated on the page we read.

Who shared Abliterlitics?

1 account on X, including @OrcaRouter, in 1 post totalling 48.6k views.

Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 12.2k posts from 4.7k X accounts over the last 21 days, 1.4k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:06 UTC. Full method.