Qwen3 32B MLX 4bit by Qwen

 ยป  All LLMs  ยป  Qwen  ยป  Qwen3 32B MLX 4bit   URL Share it on

  Arxiv:2309.00071   Arxiv:2505.09388   4-bit   4bit   Autotrain compatible   Conversational   Endpoints compatible   Quantized   Qwen3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/Qwen/Qwen3-32B-MLX-4bit 

Qwen3 32B MLX 4bit 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 MLX 4bit (Qwen/Qwen3-32B-MLX-4bit)
๐ŸŒŸ Advertise your project ๐Ÿš€

Qwen3 32B MLX 4bit Parameters and Internals

LLM NameQwen3 32B MLX 4bit
Repository ๐Ÿค—https://huggingface.co/Qwen/Qwen3-32B-MLX-4bit 
Model Size32b
Required VRAM17.4 GB
Updated2025-06-17
MaintainerQwen
Model Typeqwen3
Model Files  5.4 GB: 1-of-4   5.3 GB: 2-of-4   5.4 GB: 3-of-4   1.3 GB: 4-of-4
Quantization Type4bit
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.51.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen3 32B MLX 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 32B Unsloth Bnb 4bit40K / 39.6 GB140218
Qwen3 32B 4bit40K / 18.5 GB16841
Qwen3 32B 8bit40K / 34.9 GB13750
Qwen3 32B 128K GGUF128K / 7.8 GB1172821
Qwen3 32B40K / 65.6 GB752768392
Qwen3 32B AWQ40K / 19.4 GB10741168
Qwen3 32B GGUF40K / 7.8 GB4186069
Qwen3 32B FP840K / 34.5 GB4300851
...Distill Qwen3 32B Preview0 QAT40K / 65.8 GB24626
Qwen3 72B Embiggened40K / 146 GB12717
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen3-32B-MLX-4bit.

Rank the Qwen3 32B MLX 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? 48225 in total.

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