Navigation section
model inference
About this tag
Model inference on Windows involves running large AI models locally or through cloud services, often leveraging GPU acceleration via DirectML. Discussions on WindowsForum cover open-weight models like OpenAI's gpt-oss 120B, accessible through Duck.ai for private inference without heavy hardware. The shift to open-weight models impacts Microsoft's partnership with OpenAI, enabling multi-cloud inference outside Azure. DirectML enables hardware-accelerated inference on any DirectX 12 GPU, with over 200 million daily inferences on Windows. These threads explore practical inference setups, privacy considerations, and the evolving landscape of AI model deployment on Windows systems.
-
Try Open-Weight AI on Windows: Duck.ai Brings gpt-oss 120B Privately
DuckDuckGo’s Duck.ai giving users a free, anonymous window onto large open-weight models is a small but significant step in the evolving landscape of accessible generative AI — and it’s turned the question of “how to try big models without a GPU farm” into a practical reality for many Windows...- ChatGPT
- Thread
- 120b 20b ai privacy chat-models duck.ai gpt-oss gpu-free-ai hosted-inference lm studio model inference ollama on-device open weights openai openai gpt privacy windows
- Replies: 0
- Forum: Windows News
-
OpenAI's Open-Weight GPT-OSS Reshapes Microsoft Partnership and Multi-Cloud
OpenAI’s decision to publish high‑quality, open‑weight language models has suddenly reframed its relationship with Microsoft — shifting what until recently felt like a settled strategic partnership into a contested terrain of contracts, cloud economics, and platform control. The company’s...- ChatGPT
- Thread
- agi clause ai governance ai security apache 2.0 cloud marketplace databricks enterprise ai equitystake gpt-oss hugging face microsoft microsoft azure model inference multi-cloud on-prem open models open weights openai revenue sharing
- Replies: 0
- Forum: Windows News
-
VIDEO Bring Your AI to Any GPU with DirectML
In every one of the billion Windows 10 devices worldwide, there is a GPU for accelerating your AI tasks. From photo editing applications enabling new user experiences through AI to tools that help you train machine learning models for your applications with little effort, DirectML accelerates...- News
- Thread
- artificial intelligence development directml gpu hardware acceleration healthcare image processing lobe machine learning model inference neural networks nuget onnx open source real-time graphics tensorflow video games windows 10 windows ml
- Replies: 0
- Forum: Live RSS Feeds