SubSir/Qwen3.5-4B-Fake-AWQ-vllm

VISIONConcurrency Cost:1Model Size:4.5BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:Mar 7, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The Qwen3.5-4B model, developed by Qwen, is a 4.5 billion parameter causal language model with a vision encoder, supporting a native context length of 262,144 tokens and extensible up to 1,010,000 tokens. 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, and agentic capabilities across 201 languages and dialects, making it suitable for complex, long-horizon tasks requiring both text and visual comprehension.

Loading preview...

Qwen3.5-4B: A Multimodal Agent Foundation Model

Qwen3.5-4B is a 4.5 billion parameter multimodal model developed by Qwen, designed for exceptional utility and performance across diverse tasks. It integrates advanced capabilities in vision-language understanding, architectural efficiency, and scalable reinforcement learning.

Key Capabilities

  • Unified Vision-Language Foundation: Achieves strong performance in reasoning, coding, agent tasks, and visual understanding through early fusion training on multimodal tokens.
  • Efficient Hybrid Architecture: Utilizes Gated Delta Networks and sparse Mixture-of-Experts for high-throughput inference with minimal latency.
  • Scalable RL Generalization: Benefits from reinforcement learning scaled across millions of agent environments, enhancing real-world adaptability.
  • Global Linguistic Coverage: Supports 201 languages and dialects, facilitating inclusive worldwide deployment.
  • Ultra-Long Context: Natively handles up to 262,144 tokens, extensible to 1,010,000 tokens using YaRN scaling, ideal for long-horizon tasks.
  • Agentic Usage: Excels in tool calling, with recommended integration via Qwen-Agent for building agent applications and Qwen Code for terminal-based AI agent tasks.

Good for

  • Applications requiring unified vision-language understanding and reasoning.
  • Multilingual applications needing broad language support.
  • Agent development and complex tool-use scenarios.
  • Processing and generating content for ultra-long texts and videos.
  • Tasks demanding high-throughput inference and efficient resource utilization.

Finetunes
1 models