What are the hardware requirements for Qwen3 30B A3B?

Qwen3 30B A3B requires approximately 61.1 GB of VRAM and supports a context window of 40K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3 30B A3B and how large is it?

Qwen3 30B A3B is developed by Qwen, a model with 30b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Qwen3 30B A3B perform on standard benchmarks?

Qwen3 30B A3B has the following published scores: LMSYS ELO 1327. Compare against reference models on this page or on the LLM Explorer leaderboards.

Qwen3 30B A3B by Qwen — VRAM 61.1GB, 40K context

Name: Qwen3 30B A3B
Rating: 4 (2 reviews)
Author: Qwen

Qwen3 30B A3B is an open-source language model by Qwen. Features: 30b LLM, VRAM: 61.1GB, Context: 40K, License: apache-2.0, LLM Explorer Score: 0.48, ELO: 1327.

Arxiv:2309.00071 Arxiv:2505.09388 Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-30b-a3b-... Conversational Deploy:sagemaker Endpoints compatible Qwen3 moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen3-30B-A3B

Qwen3 30B A3B Benchmarks

LMSys ELO 1327 vs 1272 (so35) 4.3%

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Qwen3 30B A3B Parameters and Internals

LLM Name	Qwen3 30B A3B
Repository 🤗	https://huggingface.co/Qwen/Qwen3-30B-A3B
Base Model(s)	Qwen3 30B A3B Base Qwen/Qwen3-30B-A3B-Base
Model Size	30b
Required VRAM	61.1 GB
Updated	2026-08-05
Maintainer	Qwen
Model Type	qwen3_moe
Model Files	4.0 GB: 1-of-16 4.0 GB: 2-of-16 4.0 GB: 3-of-16 4.0 GB: 4-of-16 4.0 GB: 5-of-16 4.0 GB: 6-of-16 4.0 GB: 7-of-16 4.0 GB: 8-of-16 4.0 GB: 9-of-16 4.0 GB: 10-of-16 4.0 GB: 11-of-16 4.0 GB: 12-of-16 4.0 GB: 13-of-16 4.0 GB: 14-of-16 4.0 GB: 15-of-16 1.1 GB: 16-of-16
Model Architecture	Qwen3MoeForCausalLM
License	apache-2.0
Context Length	40960
Model Max Length	40960
Transformers Version	4.51.0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Torch Data Type	bfloat16
Errors	replace

Rank the Qwen3 30B A3B capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Quantized Models of the Qwen3 30B A3B

Model	Likes	Downloads	VRAM
Qwen3 30B A3B GPTQ Int4	55	169347	16 GB
Qwen3 30B A3B GGUF	284	54806	9 GB
Qwen3 30B A3B AWQ	13	41826	16 GB
Qwen3 30B A3B 4bit	16	11065	17 GB
Qwen3 30B A3B MLX 4bit	24	9891	17 GB
Qwen3 30B A3B AWQ	12	4483	16 GB
Qwen3 30B A3B 128K GGUF	61	2730	9 GB
Qwen3 30B A3B 8bit	8	3619	32 GB
...wen3 30B A3B 4bit DWQ 10072025	2	30	17 GB
Qwen3 30B A3B 3bit	2	55	13 GB

Best Alternatives to Qwen3 30B A3B

Best Alternatives	Context / RAM	Downloads	Likes
...LL MASTER CODER M 1million Ctx	1024K / 84.8 GB	66	8
... 42B A3B Thinking Total Recall	986K / 84.8 GB	26	0
Qwen3 30B A3B YOYO V3	986K / 61.1 GB	11	7
...07 YOYO2 TOTAL RECALL Instruct	986K / 84.8 GB	27	1
...07 YOYO2 TOTAL RECALL Instruct	986K / 106 GB	20	0
Qwen3 30B A3B YOYO V2	986K / 61.1 GB	19	4
Qwen3 Coder 30B A3B Instruct	256K / 61.1 GB	1746771	1168
Qwen3 30B A3B Instruct 2507	256K / 61.1 GB	3937	13
Qwen3 30B A3B Instruct 2507	256K / 61.1 GB	1903736	824
...en3 Coder 30B A3B Instruct FP8	256K / 31.2 GB	1556690	191