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

JOSIE 4B Thinking by Goekdeniz-Guelmez

 »  All LLMs  »  Goekdeniz-Guelmez  »  JOSIE 4B Thinking   URL Share it on

  28   

JOSIE 4B Thinking is an open-source language model by Goekdeniz-Guelmez. Features: 4b LLM, VRAM: 8.1GB, Context: 256K, License: mit, Instruction-Based, LLM Explorer Score: 0.27.

  Ar Base model:finetune:goekdeniz-... Base model:goekdeniz-guelmez/q...   Chat   Conversational   De   En   Endpoints compatible   Es   Fr   Id   Instruct   It   Ja   Ko   Multilingual   Pt   Qwen3   Region:us   Ru   Safetensors   Sharded   Tensorflow   Th   Vi
Model Card on HF 🤗: https://huggingface.co/Goekdeniz-Guelmez/JOSIE-4B-Thinking 

JOSIE 4B Thinking Benchmarks

LLME Score: 0.26502
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
JOSIE 4B Thinking (Goekdeniz-Guelmez/JOSIE-4B-Thinking)
🌟 Advertise your project 🚀

JOSIE 4B Thinking Parameters and Internals

LLM NameJOSIE 4B Thinking
Repository 🤗https://huggingface.co/Goekdeniz-Guelmez/JOSIE-4B-Thinking 
Base Model(s)  Goekdeniz-Guelmez/Qwen3-4B-Instruct-2507-gabliterated   Goekdeniz-Guelmez/Qwen3-4B-Instruct-2507-gabliterated
Model Size4b
Required VRAM8.1 GB
Updated2026-03-28
MaintainerGoekdeniz-Guelmez
Model Typeqwen3
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   3.1 GB: 2-of-2
Supported Languagesen es fr pt it ar ko id ru vi de th ja
Model ArchitectureQwen3ForCausalLM
Licensemit
Context Length262144
Model Max Length262144
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to JOSIE 4B Thinking

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 4B Instruct 2507256K / 8.1 GB1473674320
Jan Code 4B256K / 8.9 GB222871
Jan V3 4B Base Instruct256K / 8.9 GB182760
Qwen3 4B Instruct 2507256K / 8.1 GB7903713
Qwen3 4B Instruct 2507 FP8256K / 5.2 GB4154231
Qwen3 4B Instruct 2507256K / 8.1 GB250
...search GooseReason 4B Instruct256K / 17.6 GB4767
WEBGEN 4B Preview256K / 8.1 GB147680
Qwen3 4B Instruct 2507 FP8256K / 4.4 GB13423
...B Instruct 2507 Abliterated V2256K / 8.1 GB300
Note: green Score (e.g. "73.2") means that the model is better than Goekdeniz-Guelmez/JOSIE-4B-Thinking.

Rank the JOSIE 4B Thinking 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? 52221 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