Qwen3 Omni 30B A3B Instruct

Last updated: Recently

Model Type

Text

Max Context

Max Output

Parameter Scale

Qwen3 Omni 30B A3B Instruct by Alibaba: Text model; TTFT 0.914s, 108.7 tok/s.

Input Modality

Output Modality

Inference Speed

108.678 tokens/s

Latest Release Date

9/22/2025

SDK Ecosystem

artificial-analysismanufactureraa-bootstrap

Model Overview Fields

name

Qwen3 Omni 30B A3B Instruct

Release date

9/22/2025

Performance

108.678 tokens/s

model_creator.name

Alibaba

AA Evaluation Scores

AA Intelligence Index

10.7

AA Coding Index

7.2

AA Math Index

52.3

MMLU Pro

0.725

GPQA

0.62

HLE

0.051

LiveCodeBench

0.422

SciCode

0.186

Math-500

AIME

AIME 2025

0.523

IFBench

0.312

LCR

TerminalBench Hard

0.015

TAU2

0.164

Output Speed (tokens/s)

108.678 tok/s

TTFT (s)

0.914s

First Answer Token (s)

0.914s

Alibaba

◎

Qwen3 Omni 30B A3B Instruct

$0.25/M$0.97/M

Qwen3 Omni 30B A3B Instruct by Alibaba: Text model; TTFT 0.914s, 108.7 tok/s.

There are no reviews for this model yet.

artificial-analysismanufactureraa-bootstrap

0.0