Qwen3 32B GGUF by unsloth

 ยป  All LLMs  ยป  unsloth  ยป  Qwen3 32B GGUF   URL Share it on

  Arxiv:2309.00071   Autotrain compatible Base model:quantized:qwen/qwen...   Base model:qwen/qwen3-32b   Conversational   En   Endpoints compatible   Gguf   Imatrix   Q2   Quantized   Qwen   Qwen3   Region:us   Unsloth
Model Card on HF ๐Ÿค—: https://huggingface.co/unsloth/Qwen3-32B-GGUF 

Qwen3 32B GGUF Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3 32B GGUF (unsloth/Qwen3-32B-GGUF)
๐ŸŒŸ Advertise your project ๐Ÿš€

Qwen3 32B GGUF Parameters and Internals

LLM NameQwen3 32B GGUF
Repository ๐Ÿค—https://huggingface.co/unsloth/Qwen3-32B-GGUF 
Base Model(s)  Qwen3 32B   Qwen/Qwen3-32B
Model Size32b
Required VRAM7.7 GB
Updated2025-07-31
Maintainerunsloth
Model Typeqwen3
Model Files  18.7 GB   17.7 GB   12.3 GB   12.5 GB   16.0 GB   14.4 GB   18.7 GB   20.6 GB   19.8 GB   18.8 GB   23.2 GB   22.6 GB   26.9 GB   34.8 GB   8.3 GB   7.7 GB   11.6 GB   9.3 GB   13.0 GB   12.8 GB   16.4 GB   20.0 GB   23.2 GB   29.0 GB   39.5 GB
Supported Languagesen
GGUF QuantizationYes
Quantization Typegguf|q2|q4_k|q5_k
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.51.3
Vocabulary Size151936
Torch Data Typebfloat16

Best Alternatives to Qwen3 32B GGUF

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 32B 128K GGUF128K / 7.7 GB641624
Qwen3 32B Unsloth Bnb 4bit40K / 39.5 GB1208812
Qwen3 32B MLX 8bit40K / 33.7 GB4087
Qwen3 32B MLX 4bit40K / 17.4 GB4045
Qwen3 32B 4bit40K / 18.5 GB9121
Qwen3 32B 8bit40K / 34.9 GB8480
...ll Qwen3 32B Preview7 QAT 200K195K / 65.8 GB161
...ll Qwen3 32B Preview6 QAT 200K195K / 65.8 GB202
...ll Qwen3 32B Preview4 QAT 200K195K / 65.8 GB191
UIGEN X 32B 072740K / 65.8 GB249107
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Qwen3-32B-GGUF.

Rank the Qwen3 32B GGUF 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? 50263 in total.

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