Taewhoo/qwen3.5-9b-proteomics-rl-step25

VISIONPricing:Input $0.431 / Cached $0.0862 / Output $1.12Concurrent Unit Cost:1Model Size:9BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 26, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Qwen3.5-9B is a 9 billion parameter causal language model with a vision encoder developed by Qwen. It features a unified vision-language foundation, an efficient hybrid architecture with Gated Delta Networks and sparse Mixture-of-Experts, and scalable reinforcement learning generalization. This model excels in multimodal understanding, reasoning, coding, and agent capabilities, supporting a native context length of 262,144 tokens and extensible up to 1,010,000 tokens.

Loading preview...

What is Qwen3.5-9B?

Qwen3.5-9B is a 9 billion parameter multimodal large language model developed by Qwen, designed for exceptional utility and performance across various tasks. It integrates a unified vision-language foundation through early fusion training on multimodal tokens, allowing it to achieve cross-generational parity with Qwen3 and outperform Qwen3-VL models in reasoning, coding, agent tasks, and visual understanding benchmarks. The model utilizes an efficient hybrid architecture combining Gated Delta Networks with sparse Mixture-of-Experts for high-throughput inference with minimal latency.

Key Capabilities

  • Unified Vision-Language Understanding: Processes both text and visual inputs, outperforming previous models in multimodal benchmarks like MMMU (78.4%) and MathVision (78.9%).
  • Extended Context Length: Natively supports 262,144 tokens, extensible up to 1,010,000 tokens using YaRN scaling techniques, ideal for ultra-long text processing.
  • Scalable RL Generalization: Trained with reinforcement learning across million-agent environments for robust real-world adaptability.
  • Global Linguistic Coverage: Expanded support for 201 languages and dialects, enabling inclusive worldwide deployment.
  • Agentic Capabilities: Excels in tool calling, with strong performance on benchmarks like BFCL-V4 (66.1%) and TAU2-Bench (79.1%), and integrates with Qwen-Agent and Qwen Code.

Good for

  • Applications requiring advanced multimodal reasoning and understanding.
  • Complex coding and agent-based tasks.
  • Processing and generating content in a wide array of languages.
  • Scenarios demanding very long context windows for detailed analysis or summarization.

Finetunes
1 models