Are you compute poor?
Do you want to run Qwen3.8-27B?
Dude, if you have 8-16gb of vram or 16-24gb of MacOS memory this is by far the smartest model you can run
PrimML is doing something phenomenal, they've created a ternary version of Qwen3.8-27B
9x smaller 98.2% as smart!
Telemetry Talks episode 7 is here 🎙️
In this episode, @dianavtodea continues diving into the workshop we hosted at Cloud Native Days Romania in May, alongside our guest, Fred Navruzov, on correlating #OpenTelemetry with anomaly detection. We also explore how the VictoriaMetrics #MCP server and its skills bring #AI-powered #observability to your workflows. Learn how to detect anomalies faster and interact with your #metrics, #logs, and #traces using natural language.
👉 Watch now: https://t.co/EHflpNCSiW
#TelemetryTalks
Looking for a better local model that runs on a MacBook Air?
Our latest update brings full Gemma 4 12B support to Google AI Edge Gallery app on Mac.
✨ Multimodal: Vision & Audio inputs
🎛️ Configurable vision token budgets
⚡️ MTP for blazing-fast inference
💻 Optimized to run on 16GB Macs!
Download it today: https://t.co/Zl7qtarGVm
Want to get to grips with building web applications in Go?
Let's Go is a clear and concise guide which packs in all you need to know about best practices, project structure and practical code patterns – incl. dependency management, authentication, databases, testing & more.
Building a working app is easy - building one that looks stunning and doesn't feel vibecoded is hard. dropping some of my favourite new features and tips (generate_image my beloved 🫶) to make your apps more beautiful in Google AI Studio.
Full guide: https://t.co/69JuKO300y