LLM EXPLORER 65,418 MODELS INDEXED

Qwen3.8 2B Heretic Max by MihaiPopa-1

By MihaiPopa-1 · 248 downloads
HF Repo ↗ Copy URL

Qwen3.8 2B Heretic Max is an open-source language model by MihaiPopa-1. Features: 2b LLM, VRAM: 4.4GB, License: apache-2.0, LLM Explorer Score: 0.26.

  Abliterated Base model:empero-ai/qwen3.8-2... Base model:finetune:empero-ai/...   Conversational   Decensored   Distillation   Edge   Empero-ai   En   Endpoints compatible   Function-calling   Heretic   Image-text-to-text   Qwen3.5   Qwen3.8   Qwen3 5   Reasoning   Region:us   Safetensors   Sft   Uncensored
Model Card on HF 🤗: https://huggingface.co/MihaiPopa-1/Qwen3.8-2B-Heretic-Max 

Qwen3.8 2B Heretic Max Parameters and Internals

LLM NameQwen3.8 2B Heretic Max
Repository 🤗https://huggingface.co/MihaiPopa-1/Qwen3.8-2B-Heretic-Max 
Base Model(s)  empero-ai/Qwen3.8-2B-Distill   empero-ai/Qwen3.8-2B-Distill
Model Size2b
Required VRAM4.4 GB
Updated2026-08-24
MaintainerMihaiPopa-1
Model Typeqwen3_5
Model Files  4.4 GB
Supported Languagesen
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.15.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.8 2B Heretic Max

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.5 2B0K / 4.5 GB2633311352
Index Translate 2B0K / 4.5 GB208965
Qwen3.5 2B Base0K / 4.5 GB80959182
WeMM Embedding 2B0K / 5.4 GB543368
...e Qwen3.5 2B Decision MLX Bf160K / 3.8 GB28012
Qwen3.5 2B0K / 4.5 GB10348718
Qwen3.8 2B Distill0K / 4.5 GB205624
Intern Decision 2B0K / 0.1 GB1629
Qwen3.5 2B Multiharness RL0K / 4.4 GB2711
Qwen3.8 2B Distill Heretic0K / 4.4 GB2261
Note: green Score (e.g. "73.2") means that the model is better than MihaiPopa-1/Qwen3.8-2B-Heretic-Max.