LLM EXPLORER 59,805 MODELS INDEXED

Qwen3.8 Flash Next Heretic 2 by trohrbaugh

By trohrbaugh · 64 downloads
HF Repo ↗ Copy URL

Qwen3.8 Flash Next Heretic 2 is an open-source language model by trohrbaugh. Features: 177.4b LLM, VRAM: 355.1GB, License: other, LLM Explorer Score: 0.31.

  Abliterated   Conversational   Decensored   Endpoints compatible   Heretic   Image-text-to-text   Qwen4 exp   Region:us   Reproducible   Safetensors   Sharded   Tensorflow   Uncensored
Model Card on HF 🤗: https://huggingface.co/trohrbaugh/Qwen3.8-Flash-Next-heretic-2 

Qwen3.8 Flash Next Heretic 2 Parameters and Internals

LLM NameQwen3.8 Flash Next Heretic 2
Repository 🤗https://huggingface.co/trohrbaugh/Qwen3.8-Flash-Next-heretic-2 
Model Size177.4b
Required VRAM355.1 GB
Updated2026-08-29
Maintainertrohrbaugh
Model Typeqwen4_exp
Model Files  9.6 GB: 1-of-33   102.0 GB: 2-of-33   8.7 GB: 3-of-33   7.0 GB: 4-of-33   8.7 GB: 5-of-33   6.8 GB: 6-of-33   8.8 GB: 7-of-33   6.9 GB: 8-of-33   8.7 GB: 9-of-33   6.9 GB: 10-of-33   8.6 GB: 11-of-33   7.0 GB: 12-of-33   8.7 GB: 13-of-33   6.8 GB: 14-of-33   8.8 GB: 15-of-33   6.9 GB: 16-of-33   8.7 GB: 17-of-33   6.9 GB: 18-of-33   8.6 GB: 19-of-33   7.0 GB: 20-of-33   8.7 GB: 21-of-33   6.8 GB: 22-of-33   8.8 GB: 23-of-33   6.9 GB: 24-of-33   8.7 GB: 25-of-33   6.9 GB: 26-of-33   8.6 GB: 27-of-33   7.0 GB: 28-of-33   8.7 GB: 29-of-33   6.8 GB: 30-of-33   8.8 GB: 31-of-33   6.9 GB: 32-of-33   9.4 GB: 33-of-33   5.2 GB
Model ArchitectureQwen4ExpForConditionalGeneration
Licenseother
Model Max Length262144
Transformers Version5.16.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace