DEV Community

# selfhosted

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
llama.cpp MTP Boost, New Gemma-4 GGUF, & Qwen 3.6 Local Benchmarks

llama.cpp MTP Boost, New Gemma-4 GGUF, & Qwen 3.6 Local Benchmarks

Comments
3 min read
Building My Own Self-Hosted VPN Infrastructure

Building My Own Self-Hosted VPN Infrastructure

Comments
5 min read
Self-hosted GitHub Actions Runner: Balancing Cost and Control

Self-hosted GitHub Actions Runner: Balancing Cost and Control

Comments
7 min read
Stop Hiring, Start Orchestrating: Running an AI Agent Company with Paperclip on Railway

Stop Hiring, Start Orchestrating: Running an AI Agent Company with Paperclip on Railway

Comments
4 min read
I priced out self-hosted AI agents on a mini PC and realized I was about to spend my weekend, not save money

I priced out self-hosted AI agents on a mini PC and realized I was about to spend my weekend, not save money

Comments
6 min read
Local AI Roundup: Qwen3-8B Acceleration, Offline Gemma Robot, & Intern-S2 Multimodal

Local AI Roundup: Qwen3-8B Acceleration, Offline Gemma Robot, & Intern-S2 Multimodal

Comments
3 min read
I loaded 30 days of real LLM traces into a live demo. Here is what they reveal

I loaded 30 days of real LLM traces into a live demo. Here is what they reveal

Comments
2 min read
Stop Paying for Cloud VMs — Self-Host Your Dev Stack on Refurbished Enterprise Hardware

Stop Paying for Cloud VMs — Self-Host Your Dev Stack on Refurbished Enterprise Hardware

Comments
5 min read
How to Expose Your Docker App Securely with Cloudflare Tunnel and a Custom Domain

How to Expose Your Docker App Securely with Cloudflare Tunnel and a Custom Domain

Comments
5 min read
I Replaced Every Cloud AI Tool with Local Models — 6 Months Later, Here's What Actually Broke

I Replaced Every Cloud AI Tool with Local Models — 6 Months Later, Here's What Actually Broke

Comments
5 min read
LLaMA.cpp Gets Qwen MTP Boost, Ring-2.6-1T for Ollama, AMD GPU Fixes

LLaMA.cpp Gets Qwen MTP Boost, Ring-2.6-1T for Ollama, AMD GPU Fixes

Comments
3 min read
Y a de petites choses qu'on peut coder soi-meme au lieu de payer un SaaS

Y a de petites choses qu'on peut coder soi-meme au lieu de payer un SaaS

Comments
5 min read
My friend wanted GitLab. He got Gitea and Nextcloud for Obsidian instead.

My friend wanted GitLab. He got Gitea and Nextcloud for Obsidian instead.

1
Comments 1
4 min read
Y a des petites choses qu'on peut coder soi-meme au lieu de payer un SaaS

Y a des petites choses qu'on peut coder soi-meme au lieu de payer un SaaS

Comments
5 min read
There are small things you can code yourself instead of paying for a SaaS

There are small things you can code yourself instead of paying for a SaaS

Comments
4 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.