Building a local inference rig: RTX 3090 with 48GB RAM running Qwen3.8-27B
MaziyarPanahi · x · 2026-08-20
A developer shared a setup featuring an RTX 3090 with 48GB of RAM, running a locally hosted Qwen3.8-27B model (Q3KXL quantization) using the SlimServe inference engine with UnslothAI Dynamic 3.0, TurboQuant, and DFlash 2. It highlights a specific hardware configuration for high-performance local LLM inference.
Related event: Modded 48GB RTX 3090 Runs 27B Model Locally at High Speeds(4 posts)→
More from Infra
- Large data centers employ only ~50-150 permanent on-site staff, Microsoft says — brezina · 2026-10-16
- Prediction: Opus 5.5-level models on laptops by 2027, backed by Qwen 27B data — cephaloform · 2026-10-16
- Oracle down 12% in a week, nearly 50% off June high as OpenAI exposure spooks market — alvelda · 2026-10-16
- US data center moratoriums top 400 — an AI bull explains why they're actually good for AI — kevinsxu · 2026-10-16
- Microsoft Research unveils Magnetar, the fastest zkVM at 10-39x speedups and post-quantum security — jedisct1 · 2026-10-16
- Bonsai 2 2B hits 120 tok/s on iPhone 18 Pro, outpaces Qwen 3.5 2B at half the memory — cephaloform · 2026-10-16