Model
NVIDIA
Qwen 3.5 122B A10BQwen3.5-122B-A10B is a multimodal vision-language Mixture-of-Experts model designed for native multimodal agent applications, supporting text, image, and video inputs.
Copied!
| Name | Size | Updated | Actions |
|---|---|---|---|
.gitattributes | 1.6 KB | June 8, 2026 UTC | |
chat_template.jinja | 7.57 KB | June 8, 2026 UTC | |
config.json | 25.53 KB | June 8, 2026 UTC | |
generation_config.json | 213 B | June 8, 2026 UTC | |
model-00001-of-00002.safetensors | 46.58 GB | June 8, 2026 UTC | |
model-00002-of-00002.safetensors | 24.61 GB | June 8, 2026 UTC | |
model.safetensors.index.json | 16.36 MB | June 8, 2026 UTC | |
preprocessor_config.json | 390 B | June 8, 2026 UTC | |
README.md | 8.5 KB | June 8, 2026 UTC | |
recipe.yaml | 311 B | June 8, 2026 UTC | |
tokenizer_config.json | 1.07 KB | June 8, 2026 UTC | |
tokenizer.json | 19.06 MB | June 8, 2026 UTC | |
video_preprocessor_config.json | 385 B | June 8, 2026 UTC | |
vocab.json | 6.41 MB | June 8, 2026 UTC |