LLM EXPLORER 57,252 MODELS INDEXED

Qwen3 30B A3B AWQ by cognitivecomputations

By cognitivecomputations · 4483 downloads
HF Repo ↗ Copy URL

Qwen3 30B A3B AWQ is an open-source language model by cognitivecomputations. Features: 30b LLM, VRAM: 16.8GB, Context: 40K, License: apache-2.0, Quantized, LLM Explorer Score: 0.21.

  Arxiv:2309.00071   4-bit   Autotrain compatible   Awq Base model:quantized:qwen/qwen...   Base model:qwen/qwen3-30b-a3b   Conversational   Endpoints compatible   Quantized   Qwen3 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/cognitivecomputations/Qwen3-30B-A3B-AWQ 

Qwen3 30B A3B AWQ Parameters and Internals

LLM NameQwen3 30B A3B AWQ
Repository 🤗https://huggingface.co/cognitivecomputations/Qwen3-30B-A3B-AWQ 
Base Model(s)  Qwen3 30B A3B   Qwen/Qwen3-30B-A3B
Model Size30b
Required VRAM16.8 GB
Updated2025-07-13
Maintainercognitivecomputations
Model Typeqwen3_moe
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   5.0 GB: 3-of-4   1.8 GB: 4-of-4
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureQwen3MoeForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.51.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Qwen3 30B A3B AWQ

Best Alternatives
Context / RAM
Downloads
Likes
...30B A3B Instruct 2507 AWQ 4bit256K / 18.1 GB74420732
...oder 30B A3B Instruct AWQ 4bit256K / 18.1 GB58289956
...30B A3B Thinking 2507 AWQ 4bit256K / 18.1 GB30699415
...oder 30B A3B Instruct AWQ 4bit256K / 18.1 GB16516223
...30B A3B Thinking 2507 AWQ 4bit256K / 16.7 GB674018
...30B A3B Instruct 2507 AWQ 4bit256K / 18.1 GB3303914
...wen3 30B A3B Thinking 2507 AWQ256K / 16.7 GB48256
...wen3 30B A3B Instruct 2507 AWQ256K / 16.7 GB35316
...en3 Coder 30B A3B Instruct AWQ256K / 16.7 GB24643
Qwen3 30B A3B AWQ40K / 16.8 GB4182613
Note: green Score (e.g. "73.2") means that the model is better than cognitivecomputations/Qwen3-30B-A3B-AWQ.