modelbenchmark.io

Qwen3.6 35B A3B FP8

Alibaba · qwen3-6-35b-a3b-fp8

Compare

Open multimodal Qwen MoE for local agents that need vision, audio, and code

Specification

most-agreed values

Context
262K
Max output
66K
Released
2026-04-17
Knowledge cutoff
Retires
Open weights
yes
Input
text, image, video, audio
Output
text

Price

US dollars per million tokens · most-agreed

Input
free
Output
free
Cache read
$0.056

Available from 4 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
hetznerfreefreefree262K262K
inferxfreefree262K66K
nearai$0.17$1.10$0.056262K8K
blueclaw131K66K

More from Alibaba

most-hosted first