Published: Tue 09 June 2026
Updated: Wed 09 September 2026
By Julian
In AI .
tags: ai links rl ml todo in-a-nutshell
Models to test
Small language models for consumer hardware
Gemma 4 12B for 16 GB RAM Laptops
Edit : Tested in another article
Paper, Articles or Videos
Series of content
Paper
Things to test
RAGs
Agents
Agents tutorial
Video series by Jetbrains.
I wasn't too happy with Pi any my local models yet. Maybe Vibe by Mistral is better, but I fear it's the models' fault.
How Jesse Vincent used coding agents and skills in 2025 and Simon Willison's way of doing so
Research driven agents is a concept originally by Andrew Karparthy to let your agents read research papers before doing the concepts and coding tasks. As my local agents tasks weren't successful yet, I haven't tested this on my own so far.
Others
Quite some time, I haven't heard about new inovations like Striped Hyena once was. I'm wondering if testing it today would be interesting as it is already from 2023, but also “just” 7B parameters large.
Also from 2023, Mixture of Experts survived—SwitchHeads paper on using MoE also on the attention layer.
As it uses the diffusion model instead of “conventional” transformers also for text generation, this model says it should be quite small for its capabilities. Gemma Diffusion by Google (Blog post ). Even more unusual, but also in its early research state are NCM: Next Concept Modeling .
Misc
nVidia RAPIDS (documentation , featured notebooks ) is NVIDIA's CUDA stack for (conventional) data science (cuDF instead of Polars/Pandas, cuML instead of scikit-learn, cuGraph instead of NetworkX, etc.)
awesome MLOps list
Practitioner's guide to Reinforcement Learning (RL)
General links
The Trillion parameter consortium is a group of scientists that wants to have a more open, fair LLM models for science.
For comparison of models, the website artificialanalysis.ai is very recommended. For direct tests by your own arena.ai formally known as lmsys's lm-arena lets you battle two modles or compare the results of SOTA models with your own prompts.
Proudly powered by Pelican , which takes great advantage of Python .
The theme is by Smashing Magazine , thanks!