Qwen
Qwen3.6-35B-A3B
Model
Qwen
Qwen3.6-35B-A3B

A multimodal Mixture of Experts (MoE) model containing 35B total parameters (3B activated)

NameSizeUpdatedActions
chat_template.jinja
7.58 KBJuly 30, 2026 UTC
checksums.blake3
1.59 KBJuly 30, 2026 UTC
config.json
22.04 KBJuly 30, 2026 UTC
configuration.json
58 BJuly 30, 2026 UTC
generation_config.json
214 BJuly 30, 2026 UTC
model-00001-of-00006.safetensors
4.66 GBJuly 30, 2026 UTC
model-00002-of-00006.safetensors
4.66 GBJuly 30, 2026 UTC
model-00003-of-00006.safetensors
4.66 GBJuly 30, 2026 UTC
model-00004-of-00006.safetensors
4.66 GBJuly 30, 2026 UTC
model-00005-of-00006.safetensors
4.48 GBJuly 30, 2026 UTC
model-00006-of-00006.safetensors
1.56 GBJuly 30, 2026 UTC
model.safetensors.index.json
12.2 MBJuly 30, 2026 UTC
preprocessor_config.json
390 BJuly 30, 2026 UTC
processor_config.json
1.16 KBJuly 30, 2026 UTC
README.md
65.79 KBJuly 30, 2026 UTC
tokenizer_config.json
1.14 KBJuly 30, 2026 UTC
tokenizer.json
19.06 MBJuly 30, 2026 UTC
video_preprocessor_config.json
385 BJuly 30, 2026 UTC
vocab.json
6.41 MBJuly 30, 2026 UTC

NVIDIA and our third-party partners use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in our marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings". Please see our Privacy Policy for more information on our privacy practices.