← All models View on HuggingFace →
Qwen: Qwen3.5-35B-A3B
qwen/qwen3.5-35b-a3b
VisionTool useJSONReasoningStreaming
The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...
Pricing
Input
$0.14 / 1M
Output
$1.00 / 1M
Specs
Context
262,144 tokens
Input
text, image, video
Output
text
Released: 2026-02
Supported parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Open weights · HuggingFace
2,933,191 downloads/mo
1,435 likes
apache-2.0 image-text-to-text