@starmexxx One thing that people never talk about is the size of the context window you are able to configure on this type of local deployment.
Because if you are able to run a good model with a 4K context window, it's not super interesting. So what did you do on your deployment?
Meet Gemma 4 12B!
A unified, encoder-free multimodal model designed to bring high-performance intelligence directly to your laptop, and released under an Apache 2.0 license.
Bridging the gap between edge efficiency and advanced reasoning. Here is what’s new with Gemma 4 12B: 👇
@thdxr And instead of going through the list one by one in a single session, could it spin up workers that do everything in parallel and follow/report progress of each of them in the main session ?
Welcome to Gemini 3.5 Flash, our most powerful model to date. It pushes the frontier of intelligence, speed, and cost putting 3.5 Flash in a class of its own.
We spent the last 6 months making sure Flash is great for real world use cases. It's available everywhere now!
Arthur Mensch (Mistral) : "aujourd'hui les ingénieurs logiciels chez Mistral n'écrivent plus de ligne de code", ce sont des "managers d'agents" ; la productivité est énorme pour un individu, mais au niveau d'une grande entreprise il reste un goulot d'étranglement organisationnel.