Qwen2.5-VL-32B

What it does

Qwen2.5-VL-32B is the open-source 32B vision-language model. Combines strong language understanding with image/video analysis. Optimized with RL.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

In addition to the original formula, we have further enhanced Qwen2.5-VL-32B's mathematical and problem-solving abilities through reinforcement learning. This has also significantly improved the model's subjective user experience, with response styles adjusted to better align with human preferences. Particularly for objective queries such as mathematics, logical reasoning, and knowledge-based Q&A, the level of detail in responses and the clarity of formatting have been noticeably enhanced. In the past five months since Qwen2-VL’s release, numerous developers have built new models on the Qwen2-VL vision-language models, providing us with valuable feedback. During this period, we focused on…from huggingface.co

• 
  Qwen3.5Feb 2026 · qwen.ai · ▲288

  The 397B native multimodal agent with 17B active params

• 
  Qwen3.5 SmallMar 2026 · huggingface.co · ▲355

  0.8B-9B native multimodal w/ more intelligence, less compute

• 
  Qwen-2.5-32B is now the best open source OCR model2025 · github.com · ▲211

  Last week was big for open source LLMs. We got: - Qwen 2.5 VL (72b and 32b) - Gemma-3 (27b) - DeepSeek-v3-0324 And a couple weeks ago we got the new mistral-ocr model. We updated our OCR benchmark to include the new models. We evaluated 1,000 documents for JSON extraction accuracy. Major takeaways: - Qwen 2.5 VL (72b and 32b) are by far the most impressive. Both landed right around 75% accuracy (equivalent to GPT-4o’s performance). Qwen 72b was only 0.4% above 32b. Within the margin of error. - Both Qwen models passed mistral-ocr (72.2%), which is specifically trained for OCR. - Gemma-3…

• 
  Qwen 2.52025 · qwenlm.github.io · ▲290

  Alibaba's latest AI model series

• 
  QwQ-32B2025 · huggingface.co · ▲197

  Matching R1 reasoning yet 20x smaller

• 
  Qwen3-235B-A22B-Thinking-25072025 · huggingface.co · ▲262

  Qwen's most advanced reasoning model yet

• 
  Spira Maxima▲578

  Video model that turns script into viral social media videos

  AI · 18d ago · spira.ai

• 
  Rill Browser▲540

  The browser where Claude Code and Codex work beside you

  AI · 18d ago · rill.love

• 
  Germany's new sovereign AI model Kolibri▲424

  Kolibri is Aleph Alpha

  AI · 20d ago · tej.as

• 
  Giving Opus 5.5 a simulated paint canvas▲392

  Paintings by AI models: programs run through a simulation of oil paint.

  AI · 21d ago · stillwet.art

• 
  PixVerse R2▲381

  A real-time world model you can explore and change

  AI · 30d ago · world.pixverse.video

• 
  Beam.win▲378

  Run AI agents on one Mac and use its windows on another

  AI · 4d ago · beam.win

• 
  Sider 5.0: Deep Research with Wisebase▲1,358

  Mimic Human Research & Save Findings in AI Knowledge Base

  AI · 2025 · sider.ai

• 
  MGX (Now Atoms)▲1,296

  Turn your ideas into products that sell

  AI · 2025 · atoms.dev

• 
  Aha▲1,152

  The world's first AI influencer marketing team

  AI · 2025 · ahacreator.com

• 
  Fluently▲976

  Start speaking English as well as your native language

  AI · 2025 · getfluently.app

• 
  TheySaid 2.0▲917

  Conversational AI surveys, interviews, user tests, polls

  AI · 2025 · theysaid.io

• 
  ツSupercut▲880

  Record your screen, share instantly, look like a PRO

  Growth · 2025 · supercut.ai