Qwen

Qwen3-30B-A3B

SIZE31B

50Quality

Text

Downloads1.1M/mo

Likes970

Language model from Qwen, 31B parameters.

Open weightsApache 2.0554/1044

Drag to turn

QwenTextPromo

Qwen3-30B-A3B

Language model from Qwen, 31B parameters.

Qwen/Qwen3-30B-A3B

Type: Text
Quality: 50 · Top 50% on the Epoch Capabilities Index
Parameters: 31B (30,532,122,624)
Downloads: 1.1M in the last 30 days
Likes: 970
Access to weights: Open download
On Hugging Face since: Apr 27, 2025
Takes in: Text
Puts out: Text
Access: Open weights
License: Apache 2.0
Rarity: Promo
Set number: 554/1044

Open on Hugging Face Quality 50 Where to run it 11 Evolution 5/8 Race it 126 tok/s Meet its creature Battle GLM-4.7-Flash

License read from the model’s Hugging Face card. Stats from Qwen’s official Hugging Face account, refreshed daily.

How good is it?

Public leaderboard scores for Qwen3-30B-A3B, refreshed daily from Epoch AI and LMArena.

Top 50% of the 277 models on the Epoch Capabilities Index: #138.

Quality is the share of a leaderboard’s models this one beats, from 0 to 100. Chat models are rated on Epoch AI’s Capabilities Index when it lists them, otherwise on LMArena; image and video models on LMArena’s image and video arenas.

Leaderboards

Epoch Capabilities Index#138 of 277
One number fitted from dozens of hard benchmarks, from science questions to agentic coding.136.2 index
LMArena Text#239 of 416
People compare two anonymous answers and vote for the better one.1,317 rating
LMArena Text · Coding#233 of 411
The text arena’s coding prompts only.1,337 rating
LMArena Text · Math#210 of 400
The text arena’s math prompts only.1,355 rating
LMArena Text · Creative writing#245 of 414
The text arena’s creative writing prompts only.1,271 rating

Benchmarks Epoch AI runs

Scores from Epoch AI and LMArena, licensed CC BY 4.0. Boards list models under their own names, so a close match is shown with the name it was scored under. Credits

Where to run it

10 providers sell Qwen3-30B-A3B through an API, and 1 Hugging Face host serves it. Prices are per million tokens, cheapest first.

CheapestHelicone$0.08 in · $0.29 out
Fastest on Hugging FaceDeepInfra126 tokens/s

API providers

Provider	Input	Output	Context
HeliconeCheapest paid`qwen3-30b-a3b`	$0.08	$0.29	41K
NanoGPT`qwen/qwen3-30b-a3b`	$0.10	$0.30	41K
Jiekou.AI`qwen/qwen3-30b-a3b-fp8`	$0.09	$0.45	41K
Deep Infra`Qwen/Qwen3-30B-A3B`	$0.12	$0.50	41K
Kilo Gateway`qwen/qwen3-30b-a3b`	$0.12	$0.50	41K
OpenRouter`qwen/qwen3-30b-a3b`	$0.12	$0.50	41K
Vercel AI Gateway`alibaba/qwen-3-30b`	$0.12	$0.50	41K
Merge Gateway`qwen/qwen3-30b-a3b`	$0.11	$1.08	131K
302.AI`qwen3-30b-a3b`	$0.11	$1.08	128K
Qiniu`qwen3-30b-a3b`	—	—	40K

Hugging Face Inference Providers

Host	Input	Output	Context	Speed	First token
DeepInfraTools	$0.12	$0.50	41K	126 tok/s	0.2s

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

Qwen3-30B-A3B

Qwen3-30B-A3B

How good is it?

Leaderboards

Benchmarks Epoch AI runs

Where to run it

API providers

Hugging Face Inference Providers

More from Qwen

Qwen-Image-2.1-Turbo

Qwen3.8 Omni Flash

Qwen-Image-2.1

Qwen3.8 Flash

Qwen3.8-Flash-Next

Qwen3.8-2.4T-A95B

Qwen3.8-27B

Qwen3.8 Max