cd /news/large-language-models/one-inference-box-dgx-spark-and-mult… · home › topics › large-language-models › article
[ARTICLE · art-174139] src=dev.to ↗ pub= topic=large-language-models verified=true sentiment=· neutral

One inference box (DGX Spark) and multiple use cases...

A developer built an experimental RAG system, RAG-LCC, and spun out a separate GitHub repo, harinezumigel-llm-stack, to manage the multiple LLMs it relies on. The project uses separate models for prompt guarding and judging rather than a single inference model, and maintains two configuration sets for switching between use cases. The developer notes that running local coding assistance on a single DGX Spark box competes with the RAG tests for compute.

recommendation

Run prompt guard and judging on separate models from your main inference model, and keep distinct switchable config sets per use case so a single box can serve multiple workflows.

more in playbook: Designing agent systems
by read1 min views3 publishedNov 22, 2026
While developing my [RAG-LCC](https://github.com/HarinezumIgel/RAG-LCC) experimental RAG, I had multiple use cases:

**RAG-LCC uses LLMs for:**

Although some of the tasks can be handled by the same LMM it is good practice to have other models then the inference one for prompt guard and judgement.

I use 2 sets of configurations, which I want to switch as convenient as possible.

Coding assistance:

I tried different models, which would be a separate discussion. But when I use local coding assistance, I cannot run the RAG tests because my Spark DGX can't provide it.

Building a RAG system taught me that managing the LLMs I use is an important part of my development flow. What started as some lines of python code has become a GitHub repo on its own.

If you want to have a look: harinezumigel-llm-stack Feedback and ideas are welcome.

── more in #large-language-models 4 stories · sorted by recency
── more on @rag-lcc 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/one-inference-box-dg…] indexed:0 read:1min 2026-11-22 · —