Zaynoid/Med-3.5-9B-EBOS-v2

VISIONConcurrent Unit Cost:1Model Size:9BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jun 17, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

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 excels in reasoning, coding, agentic tasks, and visual understanding, supporting a native context length of 262,144 tokens and extensible up to 1,010,000 tokens. This model is optimized for high-throughput inference and broad linguistic coverage across 201 languages and dialects.

Loading preview...

Overview

Qwen3.5-9B is a 9 billion parameter multimodal causal language model from Qwen, designed for exceptional utility and performance. It integrates a unified vision-language foundation that achieves strong performance across reasoning, coding, agentic tasks, and visual understanding benchmarks, often outperforming previous Qwen3-VL models. 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

  • Multimodal Learning: Early fusion training on multimodal tokens enables robust visual understanding, supporting image and video inputs.
  • Extended Context: Natively handles up to 262,144 tokens, extensible to 1,010,000 tokens using YaRN scaling for ultra-long texts.
  • Agentic Functionality: Features scalable reinforcement learning for robust real-world adaptability and excels in tool calling, supported by frameworks like Qwen-Agent and Qwen Code.
  • Global Linguistic Coverage: Expanded support for 201 languages and dialects, facilitating inclusive worldwide deployment.

Performance Highlights

Qwen3.5-9B demonstrates strong performance across various benchmarks, including:

  • 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 78.9 on MathVision, often surpassing larger models like Qwen3-VL-30B-A3B in specific vision-language tasks.
  • Agentic Tasks: Shows significant improvements in BFCL-V4 (66.1) and TAU2-Bench (79.1).

Good For

  • Applications requiring advanced multimodal understanding (images, videos).
  • Developing AI agents with robust tool-calling capabilities.
  • Tasks demanding long-context processing and multilingual support.
  • High-throughput inference scenarios leveraging frameworks like SGLang or vLLM.

Finetunes
1 models