Most small models can talk about your codebase.

Nano works inside it.

Nine billion parameters, dense. Native vision. Native reasoning. A quarter-million tokens of context. Small enough to sit on one consumer GPU and stay there — and built, like everything in the Salience family, around a single question: did the task actually get done?

Ships patches, not suggestions. Reads before it writes. Finds the cause instead of the symptom, then changes the smallest thing that fixes it.

Lives in a terminal. Plans the sequence, checks the result of each step before taking the next, and recovers from a failure rather than repeating it.

Sees what you see. Screenshots, diagrams, mockups, stack traces in an image — first-class input, not an afterthought.

Thinks without being told to. Reasoning is native and on by default. You never have to write think step by step — and you should not: this model reasons on its own, and asking makes it perform instead.

~19 GB in fp16, ~6.5 GB quantized. Pass enable_thinking=False when you want the answer and not the reasoning.