unsloth/Qwen3.5-9B

Qwen3.5-9B: A Multimodal Agentic Model

Qwen3.5-9B is a 9 billion parameter multimodal causal language model developed by Qwen, designed for exceptional utility and performance. It integrates advancements in multimodal learning, architectural efficiency, and reinforcement learning to deliver robust capabilities.

Key Capabilities

• Unified Vision-Language Foundation: Achieves strong performance across reasoning, coding, agentic tasks, and visual understanding by 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 million-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 YaRN scaling techniques.
• Tool Calling: Excels in tool calling capabilities, with recommended integration via Qwen-Agent or Qwen Code.

Good For

• Multimodal Applications: Ideal for tasks requiring both vision and language understanding, such as visual question answering, document understanding, and video summarization.
• Agentic Workflows: Strong performance in general agent benchmarks (e.g., BFCL-V4, TAU2-Bench) and visual agent tasks (e.g., ScreenSpot Pro, OSWorld-Verified).
• Long Context Processing: Suitable for applications requiring analysis of ultra-long texts, with support for up to 1,010,000 tokens.
• Multilingual Applications: Expanded support for 201 languages and dialects makes it suitable for global deployments.
• Reasoning and Coding: Demonstrates strong performance in reasoning and coding benchmarks, including HMMT and LiveCodeBench.