This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Product upvotes vs the next 3
Waiting for data. Loading
Product comments vs the next 3
Waiting for data. Loading
Product upvote speed vs the next 3
Waiting for data. Loading
Product upvotes and comments
Waiting for data. Loading
Product vs the next 3
Loading
boccaccioAI - 100% Italian LLM
A 100% Italian 700M LLM built entirely from scratch.
boccaccioAI is a 100% Italian LLM with 700M parameters, built entirely from scratch by De Lauretis Tech. No pre-trained weights, no external wrappers, just a custom tokenizer, architecture, and weights trained on Italian text. Think of it as an elementary school child: it might hallucinate details, but its grammar, syntax, and flow are flawlessly Italian. A proof-of-concept proving that sovereign LLMs are possible at scale. Running on on-demand serverless GPUs. Try it now, using italian :D!
Hi Product Hunt!
I’m Lorenzo, founder of De Lauretis Tech, and today we’re incredibly excited to share boccaccioAI with you.
Most LLMs today are fine-tuned versions of English-centric models. We wanted to see if we could build a truly independent, sovereign Italian LLM completely from scratch, and we did.
What makes boccaccioAI unique:
- 100% Custom: Custom tokenizer, custom architecture, and custom weights trained from a random initialization purely on Italian data. No third-party pre-training.
- 700M Parameters: It's small, lightweight, and runs on serverless GPUs (which spin up on-demand; expect a ~20s cold start on your first prompt!).
- The "Elementary School" Phase: Since it's small, it will hallucinate facts (it's still learning about the world!), but pay attention to its flawless Italian grammar, natural syntax, and flow. The foundation is solid.
What’s next?
This 700M model is our proof of concept. We are already preparing the training pipeline for a 7B parameter model to bring true factual knowledge, reasoning, and depth to Italian AI.
We’d love to hear your thoughts, feedback, and questions. Give it a spin and let us know what you think of the generation quality! Obviously, you will have to write in Italian 😄
About boccaccioAI - 100% Italian LLM on Product Hunt
“A 100% Italian 700M LLM built entirely from scratch.”
boccaccioAI - 100% Italian LLM was submitted on Product Hunt and earned 10 upvotes and 17 comments, placing #105 on the daily leaderboard. boccaccioAI is a 100% Italian LLM with 700M parameters, built entirely from scratch by De Lauretis Tech. No pre-trained weights, no external wrappers, just a custom tokenizer, architecture, and weights trained on Italian text. Think of it as an elementary school child: it might hallucinate details, but its grammar, syntax, and flow are flawlessly Italian. A proof-of-concept proving that sovereign LLMs are possible at scale. Running on on-demand serverless GPUs. Try it now, using italian :D!
On the analytics side, boccaccioAI - 100% Italian LLM competes within Software Engineering, Artificial Intelligence and Bots — topics that collectively have 627.2k followers on Product Hunt. The dashboard above tracks how boccaccioAI - 100% Italian LLM performed against the three products that launched closest to it on the same day.
Who hunted boccaccioAI - 100% Italian LLM?
boccaccioAI - 100% Italian LLM was hunted by De Lauretis Tech. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of boccaccioAI - 100% Italian LLM including community comment highlights and product details, visit the product overview.