Mage-VL-Cowork A Full Training Recipe to Learn Hybrid Computer Use from Evolved Harnesses
Alternatives to Mage-VL-Cowork
120 open-weight models that do the same job as Mage-VL-Cowork (4.7B vision), ranked by how close they are in task and size, then by popularity and how recent they are. Licence and VRAM are shown for each.
ZwZ2-9B is the Qwen3.5-9B-based model in Zooming-without-Zooming-v2 (ZwZ2). It learns to connect visual evidence across regions through comparison, aggregation, matching, and multi-step reasoning. Training uses full images; inference requires no zooming tools.
9.4B256K ctx Unknown licence1.5K 17Oct 2026- Same category
- Similar size (9.4B vs 4.7B)
lift is a structured extraction model from Datalab that pulls structured JSON out of PDFs and images. Pass any JSON schema and lift returns a JSON object matching it, using schema-constrained decoding to guarantee valid, well-typed output.
9.7B256K ctx OpenRAIL4.4K 210Jun 2026- Same category
- Larger (9.7B vs 4.7B)
Show the workflow once. Let the agent adapt it to the task at hand.
9.4B256K ctx Apache 2.02.2K 29Aug 2026- Same category
- Similar size (9.4B vs 4.7B)
- Commercial use OK
Fara1.5-9B is a multimodal computer use agent (CUA) for web browsers, from Microsoft Research AI Frontiers. It observes the browser through screenshots and acts on the user's behalf by emitting structured tool calls — click, type, scroll, visit URL, web search, and so on — to complete tasks…
9.4B256K ctx MIT4.4K 64May 2026- Same category
- Similar size (9.4B vs 4.7B)
- Commercial use OK
💻Github Repo • 🤗Model Collections • 📜Technical Report • 🏠Project Page
8.5B64K ctx Apache 2.013K 114Aug 2025- Same category
- Similar size (8.5B vs 4.7B)
- Commercial use OK
We're excited to unveil Qwen2-VL, the latest iteration of our Qwen-VL model, representing nearly a year of innovation.
2.2B32K ctx Apache 2.0916.8K 531Aug 2024- Same category
- Smaller (2.2B vs 4.7B)
- Commercial use OK
Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
2.1B256K ctx Apache 2.046.3K 127Oct 2025- Same category
- Smaller (2.1B vs 4.7B)
- Commercial use OK
Intern-Decision-2B is a multimodal structured decision model fine-tuned from Qwen3.5-2B. It accepts a shared state, a schema of named questions, and optional images, and returns an answer distribution for every question in one model forward pass.
2.2B256K ctx Apache 2.01.9K 19Sept 2026- Same category
- Smaller (2.2B vs 4.7B)
- Commercial use OK
Describe Anything Model 3B (DAM-3B) takes inputs of user-specified regions in the form of points/boxes/scribbles/masks within images, and generates detailed localized descriptions of images.
3Bnvidia-non-commercial-license6.9K 134Apr 2025- Same category
- Similar size (3B vs 4.7B)
LensVLM is a 9B Vision Language Model (VLM) that scans compressed images of text, then selectively expands only the relevant pages to their uncompressed form via learned tools.
9.4B256K ctx Apple Machine Learning Research License939 294Sept 2026- Same category
- Similar size (9.4B vs 4.7B)
NVIDIA Cosmos Reason – an open, customizable, 7B-parameter reasoning vision language model (VLM) for physical AI and robotics - enables robots and vision AI agents to reason like humans, using prior knowledge, physics understanding and common sense to understand and act in the real world.
8.3B125K ctx NVIDIA Open Model License15.7K 249Apr 2025- Same category
- Similar size (8.3B vs 4.7B)
- Commercial use OK
Qianfan-VL is a series of general-purpose multimodal large language models enhanced for enterprise-level multimodal applications. The models offer deep optimization for high-frequency scenarios in industrial deployment while maintaining strong general capabilities.
3.7B32K ctx Custom licence271 30Sept 2025- Same category
- Similar size (3.7B vs 4.7B)
T5Gemma is a family of lightweight yet powerful encoder-decoder research models from Google, built by adapting pretrained decoder-only Gemma models into encoder-decoder ones.
2.1B32K ctx Gemma Terms of Use33.1K 88Oct 2025- Same category
- Smaller (2.1B vs 4.7B)
Description: Fara-7B is Microsoft's first agentic small language model (SLM) designed specifically for computer use. With only 7 billion parameters, Fara-7B is an ultra-compact Computer Use Agent (CUA) that achieves state-of-the-art performance within its size class and is competitive with larger…
8.3B125K ctx MIT3.2K 622Oct 2025- Same category
- Similar size (8.3B vs 4.7B)
- Commercial use OK
Transformers PaliGemma 2 3B weights, fine-tuned with 448*448 input images on the DOCCI dataset.
3BGemma Terms of Use15.4K 15Nov 2024- Same category
- Similar size (3B vs 4.7B)
Transformers PaliGemma 2 3B weights fine-tuned on a mixture of academic tasks using 224×224 input images. PaliGemma 2 mix checkpoints are fine-tuned on a diverse set of tasks and are ready to use out of the box while pt checkpoints are pre-trained and intended for further fine-tuning.
3BGemma Terms of Use15.8K 73Nov 2024- Same category
- Similar size (3B vs 4.7B)
This repository contains the UI-Venus model from the report UI-Venus-1.5 Technical Report. UI-Venus 1.5 is a unified, end-to-end GUI Agent designed for robust real-world applications. The model family includes two dense (2B/8B) and one MoE (30B-A3B) variants to meet various downstream scenarios.
2.4B256K ctx Apache 2.03.6K 43Feb 2026- Same category
- Similar size (2.4B vs 4.7B)
- Commercial use OK
This repository contains the UI-Venus model from the report UI-Venus-1.5 Technical Report. UI-Venus 1.5 is a unified, end-to-end GUI Agent designed for robust real-world applications. The model family includes two dense (2B/8B) and one MoE (30B-A3B) variants to meet various downstream scenarios.
8.8B256K ctx Apache 2.02.3K 29Feb 2026- Same category
- Similar size (8.8B vs 4.7B)
- Commercial use OK
MiMo-Embodied, a powerful cross-embodied vision-language model that shows state-of-the-art performance in both autonomous driving and embodied AI tasks, the first open-source VLM that integrates these two critical areas, significantly enhancing understanding and reasoning in dynamic physical…
8.3B125K ctx MIT2.6K 77Nov 2025- Same category
- Similar size (8.3B vs 4.7B)
- Commercial use OK
The LLaVA-NeXT model was proposed in LLaVA-NeXT: Improved reasoning, OCR, and world knowledge by Haotian Liu, Chunyuan Li, Yuheng Li, Bo Li, Yuanhan Zhang, Sheng Shen, Yong Jae Lee.
7.6BApache 2.0146.9K 315Feb 2024- Same category
- Similar size (7.6B vs 4.7B)
- Commercial use OK
We're excited to announce improvements to our MiMo-VL (MiMo-VL-7B-RL-2508 and MiMo-VL-7B-SFT-2508), featuring enhanced performance across multiple benchmarks, improved thinking control capabilities, and better user experience.
8.3B125K ctx MIT5.7K 98Aug 2025- Same category
- Similar size (8.3B vs 4.7B)
- Commercial use OK
BLIP-2 model, leveraging Flan T5-xl (a large language model). It was introduced in the paper BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models by Li et al. and first released in this repository.
3.9B512 ctx MIT19K 95Feb 2023- Same category
- Similar size (3.9B vs 4.7B)
- Commercial use OK
ZDTaichu5.0-9B is a multimodal foundation model for general visual understanding, spatial reasoning, agentic tool use, and embodied-AI research. It combines a Qwen3.5-9B language backbone with a C-RADIOv4-H vision encoder, supports text, images and videos with any-resolution visual input.
9.8B256K ctx Unknown licence1.1K 3KSept 2026- Same category
- Larger (9.8B vs 4.7B)
Transformers PaliGemma 3B weights, fine-tuned with 224*224 input images and 256 token input/output text sequences on a mixture of downstream academic datasets. The models are available in float32, bfloat16 and float16 format for research purposes only.
2.9BGemma Terms of Use72.5K 111May 2024- Same category
- Similar size (2.9B vs 4.7B)