cd /news/ai-infrastructure/show-hn-53on-ai-server-openai-compat… · home › topics › ai-infrastructure › article
[ARTICLE · art-170174] src=dev.to ↗ pub= topic=ai-infrastructure verified=true sentiment=↑ positive

Show HN: 53ON AI Server – OpenAI-compatible server for AMD Ryzen AI Max

A developer released 53ON AI Server, an MIT-licensed, dependency-free Node.js process built on llama.cpp that runs local models on an AMD Ryzen AI Max+ 395 mini PC with 128 GB of unified memory. The server exposes OpenAI and Anthropic-compatible APIs and includes a panel for loading models, issuing per-client API keys with token quotas, and relaying to cloud providers when local models fall short. A custom llama.cpp build allocates KV cache memory as tokens arrive rather than reserving it upfront via sparse Vulkan buffers, cutting a 1B model with a 1M-token window from 8.24 GiB to 0.86 GiB at startup; it has only been tested on Strix Halo with Vulkan (RADV) on Ubuntu 24.04.

by read1 min views3 publishedNov 15, 2026

Hi HN. I run my own AI at home on a Ryzen AI Max+ 395 mini PC with 128 GB of unified memory, and this is the server it talks to. It's a single Node.js process with no dependencies, on top of llama.cpp. It speaks the OpenAI and Anthropic APIs, and it has a panel to load models, give each client an API key with a token quota, and relay cloud providers when a local model isn't enough.

We also publish our own llama.cpp build. The main change is that the KV cache takes memory as tokens arrive instead of reserving it all at load (sparse buffers on Vulkan). A 1B model with a 1M-token window starts with 0.86 GiB instead of 8.24 GiB.

It's MIT. I've only tested it on Strix Halo with Vulkan (RADV) on Ubuntu 24.04. I built it with a lot of help from Claude. Feedback and bug reports are very welcome.

── more in #ai-infrastructure 4 stories · sorted by recency
── more on @53on ai server 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/show-hn-53on-ai-serv…] indexed:0 read:1min 2026-11-15 · —