furiosa-ai/Qwen3-VL-4B-Instruct

Hugging Face
VISIONConcurrent Unit Cost:1Model Size:4BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 8, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Warm

Qwen3-VL-4B-Instruct is a 4-billion-parameter dense vision-language model from Qwen, designed for multimodal chat. It integrates a vision encoder with a transformer decoder, utilizing Interleaved-MRoPE and DeepStack for robust image and video comprehension alongside text. This model excels at visual understanding tasks including OCR, document analysis, spatial reasoning, and natively supports tool calling, making it suitable for complex multimodal applications.

Loading preview...

Overview of Qwen3-VL-4B-Instruct

Qwen3-VL-4B-Instruct is a 4-billion-parameter dense vision-language model developed by Qwen, part of the Qwen3-VL series. It is specifically designed for multimodal interactions, combining a vision encoder with a dense transformer decoder. The model leverages advanced techniques like Interleaved-MRoPE positional embeddings and DeepStack multi-level feature fusion to process images and videos seamlessly with text inputs.

Key Capabilities

  • Vision-Language Understanding: Handles OpenAI-style multimodal chat messages, accepting image_url content parts alongside text for comprehensive visual and textual analysis.
  • Diverse Visual Tasks: Proficient in tasks such as OCR, document and chart analysis, spatial reasoning, and video comprehension.
  • Native Tool Calling: Supports tool (function) calling through the hermes tool-call parser, enabling integration with external functionalities.
  • Optimized for FuriosaAI Hardware: This specific repository provides a Furiosa Executable Bundle (FXB) for efficient deployment on FuriosaAI RNGD with Furiosa-LLM, running with a tensor-parallel size of 8 PEs per card.

Good For

  • Applications requiring robust multimodal chat capabilities that combine image, video, and text inputs.
  • Use cases involving visual understanding like analyzing documents, charts, or performing OCR.
  • Developers looking to integrate tool-calling functionality into their vision-language applications.
  • Users seeking optimized performance on FuriosaAI hardware for vision-language tasks.

Finetunes
1 models