Qwen
Qwen: Qwen3.5-35B-A3B
qwen/qwen3.5-35b-a3b
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 performance is comparable to that of the Qwen3.5-27B.
Input
$0.15
/ 1M tokens
Output
$1
/ 1M tokens
Context window
262.14K
tokens
Limits
Context
262,144
tokens
Max output
16,384
6.3% of the context window
Parameters
35,951,822,704
Model facts
Author
Qwen
Tokenizer
Qwen3
Modality
Text + Image + Video -> Text
License
Apache-2.0
Created
Feb 25, 2026
Hugging Face
Qwen/Qwen3.5-35B-A3B
Default generation parameters
temperature
1
top_k
20
top_p
0.95
Publication status
Hugging Face: verifiedLicense: publishedParameter count: published
Modalities
Input · TextInput · ImageInput · VideoOutput · Text
Generation controls
Frequency penaltyInclude reasoningLogit biasLogprobsMax tokensMin pPresence penaltyReasoningRepetition penaltyResponse formatSeedStopStructured outputsTemperatureTool choiceToolsTop kTop logprobsTop p
Capability scores
19.3
Intelligence index
Better than 46% of models compared