GraySoft
Model Comparison

davidau/openai-gpt-oss-20b-abliterated-uncensored-neo-imatrix-ggufvsmlabonne/meta-llama-3.1-8b-instruct-abliterated-gguf

Side-by-side comparison of davidau/openai-gpt-oss-20b-abliterated-uncensored-neo-imatrix-gguf and mlabonne/meta-llama-3.1-8b-instruct-abliterated-gguf: downloads, license, context length, tasks, and benchmarks.

davidau/openai-gpt-oss-20b-abliterated-uncensored-neo-imatrix-gguf

DavidAU · text-generation

Specialized uncensored/abliterated quants for new OpenAI 20B MOE - Mixture of Experts Model at 80+ T/S. See settings and special instructions for using abliterated models below. NEW! - HERETIC, uncensored version is here: [ https://huggingface.co/DavidAU/OpenAi-GPT-oss-20b-HERET…

mlabonne/meta-llama-3.1-8b-instruct-abliterated-gguf

mlabonne · —

!image/png 🦙 Llama 3.1 70B Instruct lorablated This is an uncensored version of Llama 3.1 8B Instruct created with abliteration (see this article to know more about it). Special thanks to @FailSpy for the original code and technique. Please follow him if you're interested in ab…

Side-by-side Specifications

davidau/openai-gpt-oss-20b-abliterated-uncensored-neo-imatrix-ggufmlabonne/meta-llama-3.1-8b-instruct-abliterated-gguf
AuthorDavidAUmlabonne
Pipeline Tasktext-generation
Librarytransformers
Downloads49,38922,885
Likes483177
LicenseUnknownUnknown
Context Length
Created2025-08-072024-07-24
Last Modified2025-11-172024-08-03
Tags
ggufgpt_ossgpt-ossopenaimxfp4programmingcode generationcodecodingcoder
transformersggufabliterateduncensoredbase_model:meta-llama/Llama-3.1-8B-Instructbase_model:quantized:meta-llama/Llama-3.1-8B-Instructlicense:llama3.1endpoints_compatibleregion:usconversational

View full details: davidau/openai-gpt-oss-20b-abliterated-uncensored-neo-imatrix-gguf · mlabonne/meta-llama-3.1-8b-instruct-abliterated-gguf