Qwen3.5 0.8B (Non-reasoning)

Last updated: Recently

Model Type

Text

Max Context

Max Output

Parameter Scale

Qwen3.5 0.8B Non reasoning by Alibaba: Text model; TTFT 0.439s, 266.6 tok/s.

Input Modality

Output Modality

Inference Speed

266.637 tokens/s

Latest Release Date

3/2/2026

SDK Ecosystem

artificial-analysismanufactureraa-bootstrap

Model Overview Fields

name

Qwen3.5 0.8B (Non-reasoning)

Release date

3/2/2026

Performance

266.637 tokens/s

model_creator.name

Alibaba

AA Evaluation Scores

AA Intelligence Index

9.9

AA Coding Index

AA Math Index

MMLU Pro

GPQA

0.236

HLE

0.049

LiveCodeBench

SciCode

0.029

Math-500

AIME

AIME 2025

IFBench

0.216

LCR

0.067

TerminalBench Hard

TAU2

0.652

Output Speed (tokens/s)

266.637 tok/s

TTFT (s)

0.439s

First Answer Token (s)

0.439s

Alibaba

◎

Qwen3.5 0.8B (Non-reasoning)

$0.01/M$0.05/M

Qwen3.5 0.8B Non reasoning by Alibaba: Text model; TTFT 0.439s, 266.6 tok/s.

There are no reviews for this model yet.

artificial-analysismanufactureraa-bootstrap

0.0