Mer0vin8ian/Qwen3.5-9B
Qwen3.5-9B is a 9 billion parameter multimodal causal language model developed by Qwen, featuring a unified vision-language foundation and an efficient hybrid architecture. It supports a native context length of 262,144 tokens, extensible up to 1,010,000 tokens, and excels in multimodal reasoning, coding, agentic tasks, and visual understanding across 201 languages. This model is optimized for high-throughput inference and robust real-world adaptability through scalable reinforcement learning.
Loading preview...
Qwen3.5-9B: A Multimodal Agent Foundation Model
Qwen3.5-9B is a 9 billion parameter multimodal causal language model developed by Qwen, designed for exceptional utility and performance. It integrates significant advancements in multimodal learning, architectural efficiency, and reinforcement learning.
Key Capabilities
- Unified Vision-Language Foundation: Achieves strong performance across reasoning, coding, agentic tasks, and visual understanding benchmarks through early fusion training on multimodal tokens.
- Efficient Hybrid Architecture: Utilizes Gated Delta Networks combined with sparse Mixture-of-Experts for high-throughput inference with minimal latency.
- Scalable RL Generalization: Features reinforcement learning scaled across millions of agent environments for robust real-world adaptability.
- Global Linguistic Coverage: Supports 201 languages and dialects, enabling inclusive worldwide deployment.
- Extended Context Length: Natively handles 262,144 tokens, extensible up to 1,010,000 tokens using RoPE scaling techniques like YaRN.
- Tool Calling: Excels in tool calling capabilities, with recommended integration via Qwen-Agent and Qwen Code.
Benchmarks and Performance
Qwen3.5-9B demonstrates strong performance across various benchmarks, often outperforming previous Qwen models and competitive alternatives in its size class. Notable scores include:
- Language: Achieves 82.5 on MMLU-Pro, 91.1 on MMLU-Redux, and 88.2 on C-Eval.
- Vision Language: Scores 78.4 on MMMU, 70.1 on MMMU-Pro, and 85.7 on Mathvista (mini).
- Agentic Tasks: Shows significant improvements in general agent benchmarks like BFCL-V4 (66.1) and TAU2-Bench (79.1).
- Multilingualism: Performs well on multilingual benchmarks such as MMMLU (81.2) and MMLU-ProX (76.3).
Recommended Use Cases
This model is ideal for applications requiring advanced multimodal understanding, complex reasoning, code generation, and agentic behaviors. Its extensive language support and long context handling make it suitable for global deployments and tasks involving large documents or detailed visual analysis.