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 ARC MLX 4bit by mlx-community

 »  All LLMs  »  mlx-community  »  Qwen3 4B ARC MLX 4bit   URL Share it on

  280   

Qwen3 4B ARC MLX 4bit is an open-source language model by mlx-community. Features: 4b LLM, VRAM: 2GB, Context: 256K, License: apache-2.0, Quantized, LLM Explorer Score: 0.27.

  4-bit   4bit   Arc   Arc-agi   Arc-agi-2   Arc-prize Dataset:arc-prize-2026-arc-agi...   Mlx   Puzzle-solving   Qlora   Quantized   Qwen3   Region:us   Safetensors   Test-time-training
Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwen3-4B-ARC-MLX-4bit 

Qwen3 4B ARC MLX 4bit Benchmarks

LLME Score: 0.27064
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3 4B ARC MLX 4bit (mlx-community/Qwen3-4B-ARC-MLX-4bit)
🌟 Advertise your project 🚀

Qwen3 4B ARC MLX 4bit Parameters and Internals

LLM NameQwen3 4B ARC MLX 4bit
Repository 🤗https://huggingface.co/mlx-community/Qwen3-4B-ARC-MLX-4bit 
Base Model(s)  sorokin/qwen3_4b_grids15_sft139   sorokin/qwen3_4b_grids15_sft139
Model Size4b
Required VRAM2 GB
Updated2026-04-12
Maintainermlx-community
Model Typeqwen3
Model Files  2.0 GB
Quantization Type4bit
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version4.53.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size16
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen3 4B ARC MLX 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...Instruct 2507 Unsloth Bnb 4bit256K / 3.5 GB9555414
Agent 4b256K / 8.1 GB4510
Qwen3 4B Self Thinking 16bit256K / 8.1 GB13100
...wen3 4B Thinking 2507 MLX 4bit256K / 2.3 GB6479012
...wen3 4B Thinking 2507 MLX 8bit256K / 4.3 GB664767
...Instruct Haiku 4.5 Merged FP16256K / 8.1 GB421
Qwen3 4B Instruct 2507 4bit256K / 2.3 GB161639
Qwen3 4B Finetune Merged 4bit256K / 3.5 GB210
Jan V3 4B Base Instruct 4bit256K / 2.3 GB5412
...Thinking 2507 Unsloth Bnb 4bit256K / 3.5 GB78242
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen3-4B-ARC-MLX-4bit.

Rank the Qwen3 4B ARC 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? 53972 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