Apple Silicon MLX

imagem 38

Ollama v0.34.0 Brings ChatGPT Desktop Integration and Performance Boosts

Leave a Comment / AI & Machine Learning /

The latest Ollama release, v0.34.0, introduces direct integration with ChatGPT Desktop, letting you use your locally hosted Ollama models without leaving the ChatGPT interface. Once set up through the Ollama app on macOS, you can keep your existing workflow while running open models side by side. This update also improves structured output performance on Apple […]

Ollama v0.34.0 Brings ChatGPT Desktop Integration and Performance Boosts Read More »

imagem 15

Ollama 0.34.0-rc1 Adds ChatGPT Desktop Integration and Apple Silicon Optimizations

Leave a Comment / AI & Machine Learning /

You can now run Ollama models directly inside ChatGPT Desktop, letting you keep your current workflow while using open models. On macOS, setup is handled right from the Ollama app. The update also brings faster structured output on Apple Silicon, support for tool search and response compaction in OpenAI-compatible clients, and correct image handling through

Ollama 0.34.0-rc1 Adds ChatGPT Desktop Integration and Apple Silicon Optimizations Read More »

imagem 41

llama.cpp Release b10159 Brings FWHT Kernel to Metal Backend

Leave a Comment / AI & Machine Learning /

We’re excited to announce a new build of llama.cpp (b10159), which includes a performance-boosting addition for Apple Silicon users. This release introduces the Fast Walsh-Hadamard Transform (FWHT) kernel into the Metal backend, improving the efficiency of certain mathematical operations during model inference. While the change is low-level, it helps streamline computation on macOS and iOS

llama.cpp Release b10159 Brings FWHT Kernel to Metal Backend Read More »

imagem 40

Ollama v0.32.5 Fixes NVFP4 Output Quality Bug on Apple Silicon

Leave a Comment / AI & Machine Learning /

Ollama v0.32.5 Release Notes The latest point release, Ollama v0.32.5, resolves a significant bug affecting users running NVFP4‑based models such as Laguna on Apple Silicon Macs. A flaw in the MLX Metal backend could previously degrade output quality, leading to less accurate or lower‑fidelity responses from these models. With the fix in place, self‑hosted users

Ollama v0.32.5 Fixes NVFP4 Output Quality Bug on Apple Silicon Read More »

imagem 35

Ollama v0.32.5-rc0 Released with MLX Update

Leave a Comment / AI & Machine Learning /

The latest release candidate of Ollama, version 0.32.5-rc0, brings an update to the MLX backend. This improvement enhances compatibility and performance for users running Ollama on Apple Silicon hardware. Self-hosted users can expect better integration with the latest MLX features, ensuring a smoother inference experience. As a pre-release, it’s an opportunity to test the updated

Ollama v0.32.5-rc0 Released with MLX Update Read More »

RSS FEED
RSS FEED