Ollama
ASUS unveils compact XG Core external Radeon RX 9060 XT GPU
ASUS has announced the XG Core Radeon RX 9060 XT LP 16GB GDDR6, an external graphics dock designed to add discrete GPU power to compatible laptops, gaming handhelds and…
Docker: A read-only AI code reviewer invented a CVE and a fake attack
A self-hosted AI code review bot with strictly read-only permissions still produced a confident, fully fabricated security report, according to Docker's sixth Coding…
Ollama adds text-to-speech with Phonon models from Gradium, starting on macOS
Ollama can now turn text into speech, with Phonon as its first speech model. Phonon is a family of small text-to-speech models from Gradium, and support is available on…
Cloudflare's Clef decision model now runs locally and on Ollama's cloud
Clef, a 27B multimodal decision model from Cloudflare, is now available on Ollama, where users can run it locally or on Ollama's cloud. According to Ollama, the model…
Reflection's open-weight Beam model is free on Ollama for a limited time
Reflection's first open-weight model, Beam, is now generally available, and Ollama is offering it for free for a limited time through Ollama Cloud. According to Ollama…
Ollama Cloud models now run inside Fly.io Sprites for safer AI agents
Ollama Cloud now works inside Fly.io Sprites, the sandboxed Linux computers Fly.io designed for AI agents. A new Ollama Connector lets a Sprite call Ollama's cloud…
Ollama adds decision models for fast, typed answers on local machines
Ollama now supports decision models based on TypeSafe's Jev API, letting a model running on a user's own machine answer several named questions about a piece of text in…