Top 5 local LLMs:
1. GLM-4.5-air: best agentic/coding model that runs on consumer hardware at very decent speeds. Rivals Claude 4-sonnet.
2. Nousresearch/hermes-70B: the only model that will do whatever you ask, and tell you whatever you want to know. Literally critical to have.
3. GPT-OSS-120B: very intelligent it’s like having 4o at home, great context window, great agent
4. Qwen3-coder-30B-3A-instruct: very good coding agent, excellent workhorse, incredibly fast
5. Mistral-magistral-small: very fast, excellent agent, great coder, multimodal, punches way, way, above its size.
I would be okay never using a proprietary llm, although given the subsidised compute I will continue to use them since I’m getting free leverage.
I’ve built my forecasts on countless data points that have proven extremely accurate over the years
I just happened to stumble across another one that aligns perfectly with my thesis
$6900 is top of channel for $ETH
We’re open-sourcing everything.
All the projects built during the Nano Banana Hackathon are now released as open-source.
Since AI Studio supports remixing, you can easily adapt and reuse them.
They may not have been huge projects, but it was a great opportunity to truly experience the value and potential of Nano Banana.
And yes—every single line was vibe-coded without writing a single line of code directly. You can do it too!
Now it’s time to build again! 🔥
Huge thanks to Google for releasing such an amazing model. @GoogleAIStudio@OfficialLoganK
2. @amazon released Kiro, an agentic IDE that turns vibe coding into production-ready apps.
It automatically creates specs, requirements docs, and task lists without you asking.
Powered by Sonnet 4 with intelligent hooks that handle tests and documentation in the background.