GPT Oss 20B RichardErkhov Heresy by MuXodious

 »  All LLMs  »  MuXodious  »  GPT Oss 20B RichardErkhov Heresy   URL Share it on

GPT Oss 20B RichardErkhov Heresy is an open-source language model by MuXodious. Features: 20b LLM, VRAM: 13.8GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.24.

  Arxiv:2508.10925   8-bit   Abliterated Base model:finetune:openai/gpt...   Base model:openai/gpt-oss-20b   Conversational   Decensored   Endpoints compatible   Gpt oss   Heretic   Mxfp4   Region:us   Safetensors   Sharded   Tensorflow   Uncensored   Vllm

GPT Oss 20B RichardErkhov Heresy Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

GPT Oss 20B RichardErkhov Heresy Parameters and Internals

LLM NameGPT Oss 20B RichardErkhov Heresy
Repository 🤗https://huggingface.co/MuXodious/gpt-oss-20b-RichardErkhov-heresy 
Base Model(s)  GPT Oss 20B   openai/gpt-oss-20b
Model Size20b
Required VRAM13.8 GB
Updated2026-07-17
MaintainerMuXodious
Model Typegpt_oss
Model Files  4.9 GB: 1-of-3   4.9 GB: 2-of-3   4.0 GB: 3-of-3
Model ArchitectureGptOssForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.57.6
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|endoftext|>
Vocabulary Size201088

Best Alternatives to GPT Oss 20B RichardErkhov Heresy

Best Alternatives
Context / RAM
Downloads
Likes
GPT Oss 20B128K / 13.8 GB72700334788
OTel LLM 20B Reasoning128K / 83.8 GB31601
GPT Oss 20B128K / 13.8 GB1641647
Context 1128K / 41.8 GB726414
GPT Oss Safeguard 20B128K / 13.8 GB154333239
OptiMind SFT128K / 42 GB15767102
GPT Oss 20B Heretic Ara V4128K / 13.8 GB533913
GPT Oss 20B BF16128K / 41.6 GB9687434
GPT Oss 20B Abliterated128K / 41.6 GB8263
Aryabhata 2.0128K / 41.8 GB1275
Note: green Score (e.g. "73.2") means that the model is better than MuXodious/gpt-oss-20b-RichardErkhov-heresy.

Rank the GPT Oss 20B RichardErkhov Heresy Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 55138 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a