library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3.5-9B/blob/main/LICENSE
pipeline_tag: image-text-to-text
base_model:
- Qwen/Qwen3.5-9B-Base
Qwen3.5-9B
[!Note]
This model was trained in BF16/TF32 with Adam on Chain of Thought ONLY
This model shows a massive increase in uncensored and unfiltered results without any direct image to text training or assistance response training.
In testing around 5 out of every 100 images would return with the censored result. Compared to 98 out of 100 returning censored on the untrained model.
Qwen3.5 Highlights
Qwen3.5 features the following enhancement:
Unified Vision-Language Foundation: Early fusion training on multimodal tokens achieves cross-generational parity with Qwen3 and outperforms Qwen3-VL models across reasoning, coding, agents, and visual understanding benchmarks.
Efficient Hybrid Architecture: Gated Delta Networks combined with sparse Mixture-of-Experts deliver high-throughput inference with minimal latency and cost overhead.
Scalable RL Generalization: Reinforcement learning scaled across million-agent environments with progressively complex task distributions for robust real-world adaptability.
Global Linguistic Coverage: Expanded support to 201 languages and dialects, enabling inclusive, worldwide deployment with nuanced cultural and regional understanding.
Next-Generation Training Infrastructure: Near-100% multimodal training efficiency compared to text-only training and asynchronous RL frameworks supporting massive-scale agent scaffolds and environment orchestration.