Alibaba has open-sourced Qwen-UI-Agent, a GUI agent foundation model that operates across mobile, desktop, web, and deep-search environments on real hardware rather than relying on simulation. It achieves top benchmark results: 82.1% on MobileWorld, 79.5% on OSWorld-Verified, and first on WebArena. It also introduces MobileWorld-Real, a 400+ task benchmark on 100+ phones and 150+ apps, with a 92.2% success rate.
- Supports command-line execution alongside standard GUI operations and batches multiple actions into a single decision step to shorten trajectories.
- Built-in safety layer refuses illegal or high-risk requests outright and pauses at sensitive operations (payments, data deletion, privacy grants) for explicit user confirmation.
- Trained via online reinforcement learning on trajectories exceeding 100 steps, paired with adaptive curriculum learning to progressively tackle longer tasks.
- Supports command-line execution alongside standard GUI operations and batches multiple actions into a single decision step to shorten trajectories.
- Built-in safety layer refuses illegal or high-risk requests outright and pauses at sensitive operations (payments, data deletion, privacy grants) for explicit user confirmation.
- Trained via online reinforcement learning on trajectories exceeding 100 steps, paired with adaptive curriculum learning to progressively tackle longer tasks.
Google's release of Gemma 4 marks a major turning point for open-source AI, offering a versatile family of multimodal models under a permissive Apache 2.0 license. Built using Gemini 3 technology, these models demonstrate massive leaps in math and coding performance, rivaling much larger proprietary systems while remaining efficient enough to run on local hardware ranging from smartphones to high-end GPUs. This release positions Google as a formidable competitor in the open-weights ecosystem, prioritizing user ownership and deployment efficiency.
* Apache 2.0 license
* Multimodal intelligence
* Local hardware deployment
* Massive benchmark leaps
* Efficient MoE architecture
**Models**
* E2B: Mobile efficiency
* E4B: Edge specialist
* 26B MoE: Speed meets intelligence
* 31B Dense: Top-tier performance
* Apache 2.0 license
* Multimodal intelligence
* Local hardware deployment
* Massive benchmark leaps
* Efficient MoE architecture
**Models**
* E2B: Mobile efficiency
* E4B: Edge specialist
* 26B MoE: Speed meets intelligence
* 31B Dense: Top-tier performance
Google DeepMind has released the Gemma 4 12B, a dense multimodal model featuring an encoder-free architecture. Unlike previous iterations that used separate vision and audio encoders, this model allows these modalities to flow directly into the LLM backbone. This streamlined design reduces latency and memory overhead, allowing the model to perform agentic reasoning tasks on consumer laptops with as little as 16 GB of VRAM while approaching the performance levels of much larger models like the 26B MoE variant.
- Unified decoder-only architecture for text, image, video, and native audio input.
- Encoder-free design using a 35M vision embedder and direct raw audio wave projection.
- Optimized to run locally on Apple Silicon Macs and consumer GPU laptops.
- Released under an Apache 2.0 license with support for llama.cpp, MLX, vLLM, and Ollama.
- Unified decoder-only architecture for text, image, video, and native audio input.
- Encoder-free design using a 35M vision embedder and direct raw audio wave projection.
- Optimized to run locally on Apple Silicon Macs and consumer GPU laptops.
- Released under an Apache 2.0 license with support for llama.cpp, MLX, vLLM, and Ollama.
Mistral Small 3.1 is an open-source multimodal AI model optimized for consumer hardware, offering strong performance in text and image processing, multilingual capabilities, and a balance between performance and accessibility. While excelling in many areas, it has limitations in long-context tasks and Middle Eastern language support.
Qwen2.5-VL, the latest vision-language model from Qwen, showcases enhanced image recognition, agentic behavior, video comprehension, document parsing, and more. It outperforms previous models in various benchmarks and tasks, offering improved efficiency and performance.
Learn how to build Llama 3.2-Vision locally in a chat-like mode, and explore its Multimodal skills on a Colab notebook.
