# Code assist and rag (instruct) in single node

**URL:** <https://forums.developer.nvidia.com/t/code-assist-and-rag-instruct-in-single-node/357616>\
**Category:** DGX Spark / GB10 Projects\
**Created:** [January 15, 2026, 7:35am UTC](https://forums.developer.nvidia.com/t/code-assist-and-rag-instruct-in-single-node/357616 "2026-01-15T07:35:15Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![g.marconi](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@g.marconi](https://forums.developer.nvidia.com/u/g.marconi)\
**Post date:** [January 15, 2026, 7:35am UTC](https://forums.developer.nvidia.com/t/code-assist-and-rag-instruct-in-single-node/357616/1 "2026-01-15T07:35:15Z")

</div>

Hi everyone,

I’m evaluating **DGX Spark / GB10** to build a **fully local developer assistant** that combines:

- **Code assistance** (code completion, refactoring, code understanding)

- **RAG** (instruct) over internal corporate website

Questions:

1. Is this combined **code assist + RAG** architecture feasible and efficient on **GB10**?

2. Would you recommend running **one single LLM** or **multiple specialized LLMs with routing**?

3. Which **LLMs** would you suggest today for:

4. Any recommended **inference stack** (TensorRT-LLM, vLLM, Triton) for this use case?

Any experience, best practices, or references on DGX Spark would be very helpful.

Thanks in advance.

---

<div class="post-metadata">

**Author:** ![g.marconi](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@g.marconi](https://forums.developer.nvidia.com/u/g.marconi)\
**Post date:** [February 13, 2026, 7:57am UTC](https://forums.developer.nvidia.com/t/code-assist-and-rag-instruct-in-single-node/357616/4 "2026-02-13T07:57:40Z")

</div>

After several tests with vLLM and NIM, I had to go back to Ollama.

With Ollama, I’m able to run more usable models:

- gpt-oss:120b-64k – inference and planner for Opencode

- qwen3-coder:30b-64k – Opencode builder

- nomic-embed-text:latest – embeddings (on Grace cpu)

- qwen2.5-coder:1.5b – autocomplete

- (nginx – gateway)

This way, I can achieve practical usage of a single Spark (Dell Pro Max GB10).

Giacomo

---

<div class="post-metadata">

**Author:** ![paulsc.liu](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@paulsc.liu](https://forums.developer.nvidia.com/u/paulsc.liu)\
**Post date:** [February 14, 2026, 2:07am UTC](https://forums.developer.nvidia.com/t/code-assist-and-rag-instruct-in-single-node/357616/5 "2026-02-14T02:07:25Z")

</div>

Thank for the information. I will give that setup a try with llama.cpp