GraySoft
Model Comparison

mlabonne/meta-llama-3.1-8b-instruct-abliterated-ggufvsmradermacher/trohrbaugh-qwen3.5-122b-a10b-heretic-i1-gguf

Side-by-side comparison of mlabonne/meta-llama-3.1-8b-instruct-abliterated-gguf and mradermacher/trohrbaugh-qwen3.5-122b-a10b-heretic-i1-gguf: downloads, license, context length, tasks, and benchmarks.

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…

mradermacher/trohrbaugh-qwen3.5-122b-a10b-heretic-i1-gguf

mradermacher · —

## About weighted/imatrix quants of https://huggingface.co/CCSSNE/trohrbaugh-Qwen3.5-122B-A10B-heretic ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/trohrbaugh-Qwen3.5-12…

Side-by-side Specifications

mlabonne/meta-llama-3.1-8b-instruct-abliterated-ggufmradermacher/trohrbaugh-qwen3.5-122b-a10b-heretic-i1-gguf
Authormlabonnemradermacher
Pipeline Task——
Librarytransformerstransformers
Downloads22,88537,014
Likes1771
LicenseUnknownUnknown
Context Length——
Created2024-07-242026-04-04
Last Modified2024-08-032026-04-05
Tags
transformersggufabliterateduncensoredbase_model:meta-llama/Llama-3.1-8B-Instructbase_model:quantized:meta-llama/Llama-3.1-8B-Instructlicense:llama3.1endpoints_compatibleregion:usconversational
transformersggufhereticuncensoreddecensoredabliteratedenbase_model:CCSSNE/trohrbaugh-Qwen3.5-122B-A10B-hereticbase_model:quantized:CCSSNE/trohrbaugh-Qwen3.5-122B-A10B-hereticlicense:apache-2.0

View full details: mlabonne/meta-llama-3.1-8b-instruct-abliterated-gguf · mradermacher/trohrbaugh-qwen3.5-122b-a10b-heretic-i1-gguf