LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Qwen3 14B MLX 4bit by Qwen

 »  All LLMs  »  Qwen  »  Qwen3 14B MLX 4bit   URL Share it on

  246   
  Arxiv:2309.00071   Arxiv:2505.09388   4-bit   4bit Base model:quantized:qwen/qwen...   Base model:qwen/qwen3-14b-base   Conversational   Mlx   Quantized   Qwen3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen3-14B-MLX-4bit 

Qwen3 14B MLX 4bit Benchmarks

LLME Score: 0.24981
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3 14B MLX 4bit (Qwen/Qwen3-14B-MLX-4bit)
🌟 Advertise your project 🚀

Qwen3 14B MLX 4bit Parameters and Internals

LLM NameQwen3 14B MLX 4bit
Repository 🤗https://huggingface.co/Qwen/Qwen3-14B-MLX-4bit 
Base Model(s)  Qwen3 14B Base   Qwen/Qwen3-14B-Base
Model Size14b
Required VRAM7.9 GB
Updated2025-08-26
MaintainerQwen
Model Typeqwen3
Model Files  5.4 GB: 1-of-2   2.5 GB: 2-of-2
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 14B MLX 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Merged16 Sft Qwen340K / 29.5 GB4930
Qwen3 14B Unsloth Bnb 4bit40K / 11.2 GB776068
Qwen3 14B MLX 4bit40K / 8.3 GB464894
Merged16 Sft Qwen3 32 240K / 29.5 GB2950
Bee1reason Arabic Qwen 14B40K / 29.5 GB121115
Bee1reason Arabic Qwen 14B40K / 29.5 GB5848
Merged16 Kto Qwen3 14B40K / 29.5 GB330
Qwen3 14B 4bit DWQ 05312540K / 8.3 GB1073
Qwen3 14B MLX 8bit40K / 15.2 GB1263
Qwen3 Codellm40K / 29.5 GB230
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen3-14B-MLX-4bit.

Rank the Qwen3 14B MLX 4bit 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? 50924 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.
Release v20241124
  Support LLM Explorer