Qwen3 4B Unsloth Bnb 4bit by unsloth

 ยป  All LLMs  ยป  unsloth  ยป  Qwen3 4B Unsloth Bnb 4bit   URL Share it on

  Arxiv:2309.00071   4-bit   4bit   Autotrain compatible Base model:quantized:qwen/qwen...   Base model:qwen/qwen3-4b   Bitsandbytes   Conversational   En   Endpoints compatible   Quantized   Qwen   Qwen3   Region:us   Safetensors   Unsloth

Qwen3 4B Unsloth Bnb 4bit Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
๐ŸŒŸ Advertise your project ๐Ÿš€

Qwen3 4B Unsloth Bnb 4bit Parameters and Internals

LLM NameQwen3 4B Unsloth Bnb 4bit
Repository ๐Ÿค—https://huggingface.co/unsloth/Qwen3-4B-unsloth-bnb-4bit 
Base Model(s)  Qwen/Qwen3-4B   Qwen/Qwen3-4B
Model Size4b
Required VRAM3.6 GB
Updated2025-06-10
Maintainerunsloth
Model Typeqwen3
Model Files  3.6 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.52.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace
Qwen3 4B Unsloth Bnb 4bit (unsloth/Qwen3-4B-unsloth-bnb-4bit)

Best Alternatives to Qwen3 4B Unsloth Bnb 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 4B 4bit40K / 2.3 GB99977
Qwen3 4B 4bit DWQ 05312540K / 2.3 GB7001
Qwen3 4B 4bit DWQ40K / 2.3 GB10583
...d Qwen3 4B Abliterated V1 4bit40K / 2.3 GB6752
...d Qwen3 4B Abliterated V1 6bit40K / 3.3 GB1432
Qwen3 4B 3kingdoms Augmented40K / 8.1 GB310
Qwen3 4B Base Unsloth Bnb 4bit32K / 3.3 GB107380
Zeta Qwen3 4B Sft32K / 8.1 GB280
Qwen3 4B 128K GGUF128K / 1.1 GB952720
Qwen3 Embedding 4B40K / 8.1 GB562546
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Qwen3-4B-unsloth-bnb-4bit.

Rank the Qwen3 4B Unsloth Bnb 4bit Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 48075 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124