Modelpublic

LLMWildling/Nemotron-175b-A13b-Coder-NVFP4

sourceHugging Faceotherupdated 2mo agoView on Hugging Face

2likes51downloads

Model Card

NVIDIA-Nemotron-3-Super-175B-A13B-Coder-NVFP4

A coding-focused expansion of NVIDIA Nemotron 3 Super 120B-A12B NVFP4.

This is a community model and is not an official NVIDIA release. It was inspired by NVIDIA's open-model, open-data, and open-tooling work around Nemotron.

Model Summary


Total Parameters	Approximately 175B
Active Parameters	Approximately 13B per token
Quantization	NVFP4 mixed-precision checkpoint
Architecture	Nemotron hybrid Mamba-2, LatentMoE, Attention, and MTP
Validated Context Length	262,144 tokens
Specialization	Agentic coding, reasoning, tool use, and multi-turn software-engineering workflows
Base Model	NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4

Focus

This iteration places additional emphasis on OpenCode-style task planning and software-engineering reasoning while retaining the broader coding behavior of the model line.

Evaluation Snapshot

In a local OpenCode evaluation, the model used a todo list to plan and carry a Flappy Bird prototype from implementation through a playable result.

[image]

Does This Work?

The public Nemotron 130B LLMWildling Canary NVFP4 provides a smaller proof point for this model line. It demonstrates direct recall of newly added domain knowledge and carries that knowledge into a follow-up task without RAG or prompt-injected context.

Intended Use

This checkpoint is intended for production coding assistants, repository analysis, agentic software-engineering systems, and tool-using workflows.

License

This model is derived from NVIDIA Nemotron 3 Super. Use is governed by the NVIDIA Nemotron Open Model License. Review the upstream model card for its full terms, safety information, limitations, and base-model details.