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
1.49 KBJuly 30, 2026 UTC
config.json
21.84 KBJuly 30, 2026 UTC
configuration.json
58 BJuly 30, 2026 UTC
generation_config.json
214 BJuly 30, 2026 UTC
model-00001-of-00005.safetensors
4.66 GBJuly 30, 2026 UTC
model-00002-of-00005.safetensors
4.66 GBJuly 30, 2026 UTC
model-00003-of-00005.safetensors
4.66 GBJuly 30, 2026 UTC
model-00004-of-00005.safetensors
4.66 GBJuly 30, 2026 UTC
model-00005-of-00005.safetensors
3.38 GBJuly 30, 2026 UTC
model.safetensors.index.json
13.64 MBJuly 30, 2026 UTC
preprocessor_config.json
390 BJuly 30, 2026 UTC
processor_config.json
1.16 KBJuly 30, 2026 UTC
README.md
65.67 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