Qwen3 30B A3B.w4a16 by nytopop

 ยป  All LLMs  ยป  nytopop  ยป  Qwen3 30B A3B.w4a16   URL Share it on

  Autotrain compatible Base model:quantized:qwen/qwen...   Base model:qwen/qwen3-30b-a3b   Compressed-tensors   Conversational   Endpoints compatible   Qwen3 moe   Region:us   Safetensors   Sharded   Tensorflow

Qwen3 30B A3B.w4a16 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3 30B A3B.w4a16 (nytopop/Qwen3-30B-A3B.w4a16)
๐ŸŒŸ Advertise your project ๐Ÿš€

Qwen3 30B A3B.w4a16 Parameters and Internals

LLM NameQwen3 30B A3B.w4a16
Repository ๐Ÿค—https://huggingface.co/nytopop/Qwen3-30B-A3B.w4a16 
Base Model(s)  Qwen3 30B A3B   Qwen/Qwen3-30B-A3B
Model Size30b
Required VRAM16.7 GB
Updated2025-08-31
Maintainernytopop
Model Typeqwen3_moe
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   5.0 GB: 3-of-4   1.7 GB: 4-of-4
Model ArchitectureQwen3MoeForCausalLM
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 30B A3B.w4a16

Best Alternatives
Context / RAM
Downloads
Likes
...07 YOYO2 TOTAL RECALL Instruct986K / 84.8 GB220
Qwen3 30B A3B YOYO V2986K / 61.1 GB121
Qwen3 30B A3B Instruct 2507256K / 61.1 GB906142519
Qwen3 Coder 30B A3B Instruct256K / 61.1 GB364250526
Qwen3 30B A3B Thinking 2507256K / 61.1 GB203915250
...wen3 30B A3B Instruct 2507 FP8256K / 31.2 GB11507667
...en3 Coder 30B A3B Instruct FP8256K / 31.2 GB8529764
...wen3 30B A3B Thinking 2507 FP8256K / 31.2 GB2917132
Qwen3 Coder 30B A3B Instruct256K / 61.1 GB668714
Qwen3 30B A3B Instruct 2507256K / 61.1 GB727611
Note: green Score (e.g. "73.2") means that the model is better than nytopop/Qwen3-30B-A3B.w4a16.

Rank the Qwen3 30B A3B.w4a16 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? 51022 in total.

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