LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Qwen3.5 397B A17B Heretic Int4 AutoRound by happypatrick

 »  All LLMs  »  happypatrick  »  Qwen3.5 397B A17B Heretic Int4 AutoRound   URL Share it on

  2488   

Qwen3.5 397B A17B Heretic Int4 AutoRound is an open-source language model by happypatrick. Features: 397b LLM, VRAM: 212.3GB, License: apache-2.0, LLM Explorer Score: 0.28.

  Arxiv:2309.05516   4-bit   Abliterated   Ar   Auto-round   Autoround Base model:quantized:radicalno... Base model:radicalnotionai/qwe...   Code   Conversational   De   En   Es   Fr   Gptq   Heretic   Int4   Ja   Ko   Moe   Pt   Quantization   Qwen3 5 moe   Reasoning   Region:us   Ru   Safetensors   Sharded   Tensorflow   Th   Uncensored   Vi   Vision   Zh
Model Card on HF 🤗: https://huggingface.co/happypatrick/Qwen3.5-397B-A17B-heretic-int4-AutoRound 

Qwen3.5 397B A17B Heretic Int4 AutoRound Benchmarks

LLME Score: 0.28145
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3.5 397B A17B Heretic Int4 AutoRound (happypatrick/Qwen3.5-397B-A17B-heretic-int4-AutoRound)
🌟 Advertise your project 🚀

Qwen3.5 397B A17B Heretic Int4 AutoRound Parameters and Internals

LLM NameQwen3.5 397B A17B Heretic Int4 AutoRound
Repository 🤗https://huggingface.co/happypatrick/Qwen3.5-397B-A17B-heretic-int4-AutoRound 
Base Model(s)  trohrbaugh/Qwen3.5-397B-A17B-heretic   trohrbaugh/Qwen3.5-397B-A17B-heretic
Model Size397b
Required VRAM212.3 GB
Updated2026-06-26
Maintainerhappypatrick
Model Typeqwen3_5_moe
Model Files  5.4 GB: 1-of-40   5.4 GB: 2-of-40   5.4 GB: 3-of-40   5.4 GB: 4-of-40   5.4 GB: 5-of-40   5.4 GB: 6-of-40   5.4 GB: 7-of-40   5.4 GB: 8-of-40   5.4 GB: 9-of-40   5.4 GB: 10-of-40   5.4 GB: 11-of-40   5.4 GB: 12-of-40   5.4 GB: 13-of-40   5.4 GB: 14-of-40   5.4 GB: 15-of-40   5.4 GB: 16-of-40   5.4 GB: 17-of-40   5.4 GB: 18-of-40   5.4 GB: 19-of-40   5.4 GB: 20-of-40   5.4 GB: 21-of-40   5.4 GB: 22-of-40   5.4 GB: 23-of-40   5.4 GB: 24-of-40   5.4 GB: 25-of-40   5.4 GB: 26-of-40   5.4 GB: 27-of-40   5.4 GB: 28-of-40   5.4 GB: 29-of-40   5.4 GB: 30-of-40   5.4 GB: 31-of-40   5.4 GB: 32-of-40   5.4 GB: 33-of-40   5.4 GB: 34-of-40   5.4 GB: 35-of-40   5.4 GB: 36-of-40   5.4 GB: 37-of-40   5.4 GB: 38-of-40   5.1 GB: 39-of-40   2.0 GB: 40-of-40
Supported Languagesen zh ja ko fr de es pt ru ar th vi
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.2.0
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.5 397B A17B Heretic Int4 AutoRound

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.5 397B A17B NVFP40K / 251.1 GB594506100
Qwen3.5 397B A17B Nvfp40K / 221.3 GB2615
Ornith 1.0 397B Mlx 8bit0K / 208.8 GB402
Note: green Score (e.g. "73.2") means that the model is better than happypatrick/Qwen3.5-397B-A17B-heretic-int4-AutoRound.

Rank the Qwen3.5 397B A17B Heretic Int4 AutoRound 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? 54597 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
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
  Support LLM Explorer