Abliterated GLM-5.3 hosted online: 1M context, FP8, zero retention

cephaloform · x · 2026-09-02

The abliteration team released abliterated-model-large-v2, based on GLM-5.3 (ranked #3 on Terminal-Bench 4.0, behind only Opus 5 and Fable). The abliterated version is aimed at offensive cyber, red teaming, and agent testing work that other models refuse, with US hosting, FP8 quantization, a 1M context window, and claimed zero input/output retention. The PSA also warns that GLM 5.3 copies on HuggingFace are not closed weights behind an API.

Related event: Abliteration Releases Guardrail-Removed Model Based on GLM-5.3(5 posts)→

Original post →

More from Models

Models channel →