Baby's first PC: 3090 with local LLM inference

QuixiAI · x · 2026-08-20

User shared a setup for a child's first PC featuring a 48GB RTX 3090 running a local inference engine (SlimServe) with a quantized Qwen2.5-72B model.

Related event: Modded 48GB RTX 3090 Runs 27B Model Locally at High Speeds(4 posts)→

Original post →

More from Infra

Infra channel →