A modded RTX 3090 with 48GB RAM runs a 27B Qwen GGUF locally via SlimServe
MaziyarPanahi · x · 2026-08-20
QuixiAI showed off a local inference setup: an RTX 3090 modded to 48GB of RAM running UnslothAI's Dynamic Qwen3.8-27B Q3KXL GGUF quantized model with TurboQuant and DFlash 2, using their own SlimServe engine. Maziyar Panahi asked about the actual tokens/s throughput — a sign that single-GPU, high-VRAM local deployment of mid-size models remains a hot topic.
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