Models

Qwen3 0.6B (Non-reasoning)

Qwen3 0.6B is a lightweight, non-reasoning variant of the Qwen3 series with only 0.6 billion parameters. It is optimized for fast inference, low latency, and minimal resource consumption, making it suitable for edge deployment, simple conversational tasks, and applications requiring rapid response times.

FastCheap
Input / 1M tokens
$0.11
Output / 1M tokens
$0.42
Output tokens/s
224.09
First-token seconds
0.89s
Supported plans
7

Benchmark history

Evaluations

15

TAU2

Measured May 14, 2026Source

Score

0.15

Terminalbench Hard

Measured May 14, 2026Source

Score

0

Lcr

Measured May 14, 2026Source

Score

0

Ifbench

Measured May 14, 2026Source

Score

0.22

Aime 25

Measured May 14, 2026Source

Score

0.1

Aime

Measured May 14, 2026Source

Score

0.02

Math 500

Measured May 14, 2026Source

Score

0.52

Scicode

Measured May 14, 2026Source

Score

0.04

Livecodebench

Measured May 14, 2026Source

Score

0.07

Hle

Measured May 14, 2026Source

Score

0.05

Gpqa

Measured May 14, 2026Source

Score

0.23

Mmlu Pro

Measured May 14, 2026Source

Score

0.23

Artificial Analysis Math Index

Measured May 14, 2026Source

Score

10.3

Artificial Analysis Coding Index

Measured May 14, 2026Source

Score

1.4

Artificial Analysis Intelligence Index

Measured May 14, 2026Source

Score

5.7

Plan availability

Products and plans that support this model

3

Discussion

Thinking... Make sure you are connected to GitHub server