furiosa-ai/Qwen3-VL-32B-Thinking

VISIONPricing:Input $0.416 / Output $1.664Concurrent Unit Cost:2Model Size:33.4BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jul 24, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Qwen3-VL-32B-Thinking is a 32-billion-parameter dense vision-language model from the Qwen3-VL series, developed by Qwen. It integrates a vision encoder with a dense transformer decoder, utilizing Interleaved-MRoPE positional embeddings and DeepStack multi-level feature fusion. This model excels at visual understanding tasks including OCR, document/chart analysis, spatial reasoning, and video comprehension, and natively supports tool calling. As the "Thinking" edition, it explicitly generates a chain-of-thought before its final answer, enhancing reasoning capabilities.

Loading preview...

Overview

Qwen3-VL-32B-Thinking is a 32-billion-parameter dense vision-language model from the Qwen3-VL series, developed by Qwen. This model is designed to process both images and text, covering a wide range of visual understanding tasks such as OCR, document and chart analysis, spatial reasoning, and video comprehension. A key differentiator of this "Thinking" edition is its ability to emit an explicit chain-of-thought before providing a final answer, which can be parsed separately.

Key Capabilities

  • Vision-Language Processing: Accepts OpenAI-style multimodal chat messages with image_url content parts alongside text.
  • Enhanced Reasoning: Generates a detailed chain-of-thought, which Furiosa-LLM can parse separately from the final response, aiding in understanding the model's decision-making process.
  • Tool Calling: Supports function calling via the hermes tool-call parser, enabling interaction with external tools.
  • Hardware Optimization: Provided with a Furiosa Executable Bundle (FXB) for optimized execution on FuriosaAI RNGD hardware, utilizing a tensor-parallel size of 32 PEs across four RNGD cards.

Good for

  • Applications requiring detailed visual understanding and analysis.
  • Use cases where explicit reasoning steps are beneficial for transparency or debugging.
  • Integrating with external tools and functions for complex tasks.
  • Deployment on FuriosaAI RNGD for high-performance inference of vision-language models.

Finetunes
1 models