Qwen3.5 4B (Reasoning)

Last updated: Recently

Model Type

Text

Max Context

Max Output

Parameter Scale

Qwen3.5 4B Reasoning by Alibaba: Text model; TTFT 0.495s, 198.5 tok/s.

Input Modality

Output Modality

Inference Speed

198.527 tokens/s

Latest Release Date

3/2/2026

SDK Ecosystem

artificial-analysismanufactureraa-bootstrap

Model Overview Fields

name

Qwen3.5 4B (Reasoning)

Release date

3/2/2026

Performance

198.527 tokens/s

model_creator.name

Alibaba

AA Evaluation Scores

AA Intelligence Index

27.1

AA Coding Index

17.5

AA Math Index

MMLU Pro

GPQA

0.771

HLE

0.078

LiveCodeBench

SciCode

0.161

Math-500

AIME

AIME 2025

IFBench

0.52

LCR

0.557

TerminalBench Hard

0.182

TAU2

0.921

Output Speed (tokens/s)

198.527 tok/s

TTFT (s)

0.495s

First Answer Token (s)

10.57s

Alibaba

◎

Qwen3.5 4B (Reasoning)

$0.03/M$0.15/M

Qwen3.5 4B Reasoning by Alibaba: Text model; TTFT 0.495s, 198.5 tok/s.

There are no reviews for this model yet.

artificial-analysismanufactureraa-bootstrap

0.0