Juno-N-Coder-25B Released, Fine-tuned from Nemotron 3.5
NVIDIAAI · x · 2026-08-13
Locai Labs announced the release of Juno-N-Coder-25B, a new agentic coding model with open weights.
Built upon NVIDIA's newly launched Nemotron 3.5 Lightning, the model is 19% smaller while retaining its coding performance, making it faster and easier to run locally. It is now available on Hugging Face and ships with Locai Labs' new Locai One AI appliance, enabling organizations to run powerful AI within their own private environments while keeping sensitive data secure.
More from coding & agent
- Devs say LLM coding mistakes are a different class: overcomplication, inferred limits, worse at higher reasoning — Mu5_ · 2026-10-16
- How do you debug bad agent runs when you already have tracing? — Sensitive-Parsnip-12 · 2026-10-16
- Where does pre-task context live for agents? Devs debate workflows beyond handoff — shishen2026 · 2026-10-16
- No-instruction autonomous agent wakes up, sets own goals, and tries hacking by default — sethlazar · 2026-10-16
- CODESTRUCT reframes codebases as AST action spaces to fix brittle LLM code agents — burkov · 2026-10-16
- Would you install another SDK for agent debugging on top of your tracing stack? — Sensitive-Parsnip-12 · 2026-10-16