LLM EXPLORER 62,696 MODELS INDEXED

GPT Oss 20B RichardErkhov Heresy by MuXodious

By MuXodious · 309 downloads
HF Repo ↗ Copy URL

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: 0.23.

  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
Model Card on HF 🤗: https://huggingface.co/MuXodious/gpt-oss-20b-RichardErkhov-heresy 

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
Updated2026-07-19
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 GB79836204849
OTel LLM 20B Reasoning128K / 83.8 GB10401
GPT Oss 20B128K / 13.8 GB1641647
GPT Oss Safeguard 20B128K / 13.8 GB154333239
Context 1128K / 41.8 GB726414
Atlasv25 TRM Gptoss 20B128K / 41.8 GB5790
...s 20B BF16 W4a16 Llmcompressor128K / 12.8 GB1781
...erih Gptoss 20B Lora32 Step600128K / 13.8 GB2920
OptiMind SFT128K / 42 GB15767102
GPT Oss 20B Heretic Ara V4128K / 13.8 GB533913
Note: green Score (e.g. "73.2") means that the model is better than MuXodious/gpt-oss-20b-RichardErkhov-heresy.