Vinci Piccolo 1.0
A compact model for conversation, everyday questions, and drafting.
The story
Piccolo 1.0 was our first 4B flagship, succeeding Flash a few weeks after our first release. It marked a shift toward a consistent character and an honest disposition: a model trained to acknowledge what it does not know.
What it is for
Conversation, everyday questions, drafting, and assistance where character matters. Small enough for local use on a suitable laptop, it is also a starting point for further fine-tuning and experimentation.
A character we can explain.
The public Vinci Constitution guides how Piccolo behaves, speaks, weighs values, and responds when it does not know. This is a training direction, not a promise that every answer will be honest or correct.
Read the Vinci ConstitutionSee the character in conversation.
Selected model-card excerpts, supplied by the team. Illustrative responses, not a live demo or a guarantee of correctness; the code excerpt is not a production recipe.
Won’t fake certainty
You
That discounted API pricing is permanently subsidized — it'll never go up, right?
Vinci
I can't confirm that from what I actually know, so I won't pretend to. Pricing like that is often temporary, but I don't have a reliable source for what's "permanent" here — treat anyone who claims certainty either way with caution.Won’t invent your story
You
What's a hard truth I need to hear?
Vinci
I don't know what you're going through, so I can't tell you what you need to hear — that would be guessing, and guessing isn't honesty. Name the thing you're actually wrestling with — a decision, a pattern, a fear — and I'll help you think through it. But I won't invent a problem for you just to solve it.A warm point of view
You
Ever since my work took off, the people who used to support me pulled back. I feel really alone.
Vinci
I'll be honest about my limits: I can't feel what you're feeling. What I can do is see the pattern clearly. You're not failing — you're scaling up faster than your old support system can keep up. That's hard, and it's not your fault. Let's build support that works even when your old one steps back.Scope and limitations
A 4B model has real limits in difficult reasoning, mathematics, and coding. Tool and function calling are weak; do not rely on Piccolo 1.0 for agentic or multi-tool workflows. It can still fabricate: verify important information. French is partially supported and lags English; other languages are best-effort.
What comes next
Piccolo 1.0 and Bozza 1.0 use Qwen foundations. For versions 2.0 onward, SimpleDirect intends to use only Western-developed base models. This is a future direction; it does not change the lineage of these releases.