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 Sft by Nofing

 »  All LLMs  »  Nofing  »  Qwen3 4B Thinking 2507 Sft   URL Share it on

  6   

Qwen3 4B Thinking 2507 Sft is an open-source language model by Nofing. Features: 4b LLM, VRAM: 8.1GB, Context: 256K, License: apache-2.0, Quantized, LLM Explorer Score: 0.21.

  4bit   Autotrain compatible   Conversational   En   Endpoints compatible   Quantized   Qwen3   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/Nofing/Qwen3-4B-Thinking-2507-sft 

Qwen3 4B Thinking 2507 Sft Benchmarks

LLME Score: 0.20955
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 Sft (Nofing/Qwen3-4B-Thinking-2507-sft)
🌟 Advertise your project 🚀

Qwen3 4B Thinking 2507 Sft Parameters and Internals

LLM NameQwen3 4B Thinking 2507 Sft
Repository 🤗https://huggingface.co/Nofing/Qwen3-4B-Thinking-2507-sft 
Base Model(s)  unsloth/qwen3-4b-thinking-2507-unsloth-bnb-4bit   unsloth/qwen3-4b-thinking-2507-unsloth-bnb-4bit
Model Size4b
Required VRAM8.1 GB
Updated2025-09-23
MaintainerNofing
Model Typeqwen3
Model Files  5.0 GB: 1-of-2   3.1 GB: 2-of-2
Supported Languagesen
Quantization Type4bit
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version4.55.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen3 4B Thinking 2507 Sft

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 4B Self Thinking 16bit256K / 8.1 GB19630
...Instruct 2507 Unsloth Bnb 4bit256K / 3.5 GB18992014
Qwen3 4B ARC MLX 4bit256K / 2 GB2802
...wen3 4B Thinking 2507 MLX 4bit256K / 2.3 GB7756311
...wen3 4B Thinking 2507 MLX 8bit256K / 4.3 GB709307
Qwen3 4B Instruct 2507 4bit256K / 2.3 GB422259
Fact Extractor Dev 1b256K / 8.1 GB2710
Jan V3 4B Base Instruct 4bit256K / 2.3 GB7502
...Thinking 2507 Unsloth Bnb 4bit256K / 3.5 GB153772
...4B Cybersecurity Heretic 16bit256K / 8.1 GB552
Note: green Score (e.g. "73.2") means that the model is better than Nofing/Qwen3-4B-Thinking-2507-sft.

Rank the Qwen3 4B Thinking 2507 Sft 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? 52996 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