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 4B Thinking 2507 Heretic CodeFeedback by JoaoZaokk

 »  All LLMs  »  JoaoZaokk  »  Qwen3 4B Thinking 2507 Heretic CodeFeedback   URL Share it on

  18   

Qwen3 4B Thinking 2507 Heretic CodeFeedback is an open-source language model by JoaoZaokk. Features: 4b LLM, VRAM: 8.1GB, Context: 256K, License: other, Instruction-Based, LLM Explorer Score: 0.28.

Base model:finetune:joaozaokk/... Base model:joaozaokk/qwen3-4b-...   Code   Conversational Dataset:iamtarun/python code i... Dataset:m-a-p/codefeedback-fil...   En   Endpoints compatible   Heretic   Instruct   Lora   Merge   Python   Qlora   Qwen3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/JoaoZaokk/Qwen3-4B-Thinking-2507-Heretic-CodeFeedback 

Qwen3 4B Thinking 2507 Heretic CodeFeedback Benchmarks

LLME Score: 0.27714
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3 4B Thinking 2507 Heretic CodeFeedback (JoaoZaokk/Qwen3-4B-Thinking-2507-Heretic-CodeFeedback)
🌟 Advertise your project 🚀

Qwen3 4B Thinking 2507 Heretic CodeFeedback Parameters and Internals

LLM NameQwen3 4B Thinking 2507 Heretic CodeFeedback
Repository 🤗https://huggingface.co/JoaoZaokk/Qwen3-4B-Thinking-2507-Heretic-CodeFeedback 
Base Model(s)  JoaoZaokk/Qwen3-4B-Thinking-2507-MiniMax-M2.1-Distill-heretic   JoaoZaokk/Qwen3-4B-Thinking-2507-MiniMax-M2.1-Distill-heretic
Model Size4b
Required VRAM8.1 GB
Updated2026-06-07
MaintainerJoaoZaokk
Model Typeqwen3
Instruction-BasedYes
Model Files  4.0 GB: 1-of-3   4.0 GB: 2-of-3   0.1 GB: 3-of-3
Supported Languagesen
Model ArchitectureQwen3ForCausalLM
Licenseother
Context Length262144
Model Max Length262144
Transformers Version5.10.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Vocabulary Size151936
Errorsreplace

Best Alternatives to Qwen3 4B Thinking 2507 Heretic CodeFeedback

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 4B Instruct 2507256K / 8.1 GB4833125869
Qwen3 4B Instruct 2507 FP8256K / 5.2 GB84028179
CyberSecQwen 4B256K / 8 GB122411
Jan Code 4B256K / 8.9 GB40377
Qwen3 4B Elderly Sft Merged256K / 8.1 GB3430
Qwen3 4B DASD 32K256K / 8 GB4460
SimpleSD 4B Instruct256K / 8.1 GB11084
Qwen3 4B Instruct 2507256K / 8.1 GB4128426
Jan V3.5 4B256K / 8.9 GB28115
Qwen3 4B FitGPT AR EN Instruct256K / 8 GB2601
Note: green Score (e.g. "73.2") means that the model is better than JoaoZaokk/Qwen3-4B-Thinking-2507-Heretic-CodeFeedback.

Rank the Qwen3 4B Thinking 2507 Heretic CodeFeedback 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? 54384 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