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

Cozum 4B by Yigit-Karaman

 »  All LLMs  »  Yigit-Karaman  »  Cozum 4B   URL Share it on

  2   

Cozum 4B is an open-source language model by Yigit-Karaman. Features: 4b LLM, VRAM: 9.1GB, License: apache-2.0, LLM Explorer Score: 0.27.

  Conversational Dataset:cenfis/alpaca-turkish-... Dataset:cohereforai/aya datase... Dataset:yigit-karaman/aya turk...   Dataset:ytu-ce-cosmos/gsm8k tr   En   Llama-factory   Qwen   Qwen3 5   Region:us   Safetensors   Sft   Sharded   Tensorflow   Tr   Turkish
Model Card on HF 🤗: https://huggingface.co/Yigit-Karaman/Cozum-4B 

Cozum 4B Benchmarks

LLME Score: 0.26725
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Cozum 4B (Yigit-Karaman/Cozum-4B)
🌟 Advertise your project 🚀

Cozum 4B Parameters and Internals

LLM NameCozum 4B
Repository 🤗https://huggingface.co/Yigit-Karaman/Cozum-4B 
Model Size4b
Required VRAM9.1 GB
Updated2026-07-22
MaintainerYigit-Karaman
Model Typeqwen3_5
Model Files  5.0 GB: 1-of-2   4.1 GB: 2-of-2
Supported Languagestr en
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.7.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Cozum 4B

Best Alternatives
Context / RAM
Downloads
Likes
GRM 2.50K / 9.3 GB426025
Qwopus3.5 4B V30K / 9.3 GB138214
DPO0K / 9.3 GB312
....6 Opus Reasoning Distilled V20K / 9.3 GB102211
Qwen35 4B Plantdisease Cpt0K / 9.1 GB1561
Qwen 3.5 4b QLORA Finetuning0K / 9.3 GB1870
...e 4.6 Opus Reasoning Distilled0K / 9.3 GB24131
QwenPaw Flash 4B0K / 10.4 GB21611
Qwen3.5 4B Mlx Vlm Nvfp40K / 3 GB840
Qwen3.5 4B MLX 4bit0K / 3 GB2308230
Note: green Score (e.g. "73.2") means that the model is better than Yigit-Karaman/Cozum-4B.

Rank the Cozum 4B 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? 55294 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