---
title: "Getting A Proprietary-Bus GPU Onto PCIe Enables Cheaper Local LLMs, For Now"
url: https://daily.dev/posts/getting-a-proprietary-bus-gpu-onto-pcie-enables-cheaper-local-llms-for-now-9vqydfswh
source_url: https://hackaday.com/2026/05/09/getting-a-proprietary-bus-gpu-onto-pcie-enables-cheaper-local-llms-for-now
type: article
source: "Hackaday"
published: 2026-05-09T08:31:17.274Z
updated: 2026-05-09T08:31:36.410Z
tags: ["gpu", "self-hosting", "local-ai"]
reading_time: 2
upvotes: 0
comments: 0
language: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Getting A Proprietary-Bus GPU Onto PCIe Enables Cheaper Local LLMs, For Now

**[Hackaday](https://daily.dev/sources/hackaday)** · 2 min read · 0 upvotes · 0 comments

## Summary

A hardware enthusiast acquired an Nvidia V100 16GB GPU for ~$100 due to its SXM2 socket (server bus, not PCIe), then used a ~$100 adapter board to connect it to a consumer motherboard. Despite being a 2017 card, it outperforms an RTX 3060 12GB in tokens-per-second for local LLM inference, though at higher idle power. The arbitrage window may close as the market catches on, but for now it's a cost-effective path to running large open-source AI models locally.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://hackaday.com/2026/05/09/getting-a-proprietary-bus-gpu-onto-pcie-enables-cheaper-local-llms-for-now>

## Similar posts on daily.dev

- [I Put a Datacenter GPU in My Gaming PC for £200](https://daily.dev/posts/i-put-a-datacenter-gpu-in-my-gaming-pc-for-200-fsqh3pkrd) · Lobsters · 5 upvotes · 0 comments
- [Industrial GPU Adapted For The Desktop](https://daily.dev/posts/industrial-gpu-adapted-for-the-desktop-80xbidkpk) · Hackaday · 0 upvotes · 0 comments
- [I added a second GPU just for local AI workloads, and it cost less than upgrading my main one](https://daily.dev/posts/i-added-a-second-gpu-just-for-local-ai-workloads-and-it-cost-less-than-upgrading-my-main-one-rnty4xi8p) · XDA Developers · 0 upvotes · 0 comments

---

Tags: [#gpu](https://daily.dev/tags/gpu), [#self-hosting](https://daily.dev/tags/self-hosting), [#local-ai](https://daily.dev/tags/local-ai)

[View this post on daily.dev](https://daily.dev/posts/getting-a-proprietary-bus-gpu-onto-pcie-enables-cheaper-local-llms-for-now-9vqydfswh)