Ask HN: What Does Your Self-Hosted LLM Stack Look Like in 2025?

Back when web development was taking off, there was always a go-to stack — something like Postgres + Django + jQuery, or .NET + Bootstrap, SQLITE. Over the years we had proven tech and proven patterns like : MVC, SPA etc...

Now that local LLMs are gaining traction, I’m wondering what the equivalent stack looks like today.

Models, Runtime, hardware and other tools.

That could rival the Claudes, ChatGPTs or Geminis, etc

Thanks

17 points | by anditherobot 1 day ago

7 comments

  • bluejay2387 1 day ago
    2x 3090's running Ollama and VLLM... Ollama for most stuff and VLLM for the few models that I need to test that don't run on Ollama. Open Web UI as my primary interface. I just moved to Devstral for coding using the Continue plugin in VSCode. I use Qwen 3 32b for creative stuff and Flux Dev for images. Gemma 3 27b for most everything else (slightly less smart than Qwen, but its faster). Mixed Bread for embeddings (though apparently NV-Embed-v2 is better?). Pydantic as my main utility library. This is all for personal stuff. My stack at work is completely different and driven more by our Legal teams than technical decisions.
  • v5v3 9 hours ago
    Ollama on a M1 MacBook pro but will be moving to a Nvidia GPU setup.
  • fazlerocks 1 day ago
    Running Llama 3.1 70B on 2x4090s with vLLM. Memory is a pain but works decent for most stuff.

    Tbh for coding I just use the smaller ones like CodeQwen 7B. way faster and good enough for autocomplete. Only fire up the big model when I actually need it to think.

    The annoying part is keeping everything updated, new model drops every week and half don't work with whatever you're already running.

  • runjake 23 hours ago
    Ollama + M3 Max 36GB Mac. Usually with Python + SQLite3.

    The models vary depending on the task. DeepSeek distilled has been a favorite for the past several months.

    I use various smaller (~3B) models for simpler tasks.

  • gabriel_dev 23 hours ago
    Ollama + mac mini 24gb (inference)
  • xyc 22 hours ago
    recurse.chat + M2 max Mac