Tag
The author reports that RTX 8000 48GB prices have fallen to around $2100 while RTX 3090 prices have roughly doubled, arguing the RTX 8000 may now be the best value 'do everything' option for running large local models in VRAM for home-lab setups.
This article details the author's experience migrating data from a Synology NAS to a UniFi UNAS Pro 8 using Robocopy, highlighting challenges such as file system limitations like Alternate Data Streams and performance traps with SMB Multichannel.
Building a Kubernetes cluster with six used office PCs for $300 provides significant cost savings compared to AWS cloud services, encouraging practical home lab setups with readily available hardware.
A user shares that they are assembling a kit designed by Cherry Takuan-san for a DIY CPU, with original designs licensed under CC BY 4.0. The CPU is similar in complexity to early-1980s 16-bit home computers.
Tanuki has built a fully functioning computer processor in a home lab by stacking custom circuit boards, and is running logic and mathematics tests on its ALU, achieving complexity similar to early-1980s 16-bit home computers.
A user shares 7-day stats of local LLMs running on a home-lab, noting MoE models dominate their RTX 3090, with Inkling-small and Ling-3.0-flash performing well, and plans to open-source their dashboard.
User shares first home-lab results running Kimi K3 on 768GB DDR5 and 2x5090 using a llama.cpp fork and Q2_K quant, reporting prefill speeds of 50-70 tps and decoding tps that increases over time.
A technical guide on setting up multicast TV distribution on a home network using ffmpeg and multicast routing protocols, with examples for local and routed scenarios.
A user seeks recommendations for running a local AI model continuously on a 24x7 openclaw setup in their home lab.
A practical guide on sequencing your own genome at home using the Oxford Nanopore MinION, covering hardware, protocol steps, and analysis tools.
A detailed home lab setup with 6x P40 GPUs running a quantized MiniMax M2.7 model, including hardware specs, benchmark results, and optimal configuration using llama.cpp.
A user describes their home data center setup with multiple high-end systems for ML experiments, training, and agentic coding.
A user built a private AI lab under his desk using RTX 5090 and RTX 4090 GPUs, running local open-source models like Qwen, DeepSeek, and Llama to avoid API costs.
A user with no lab experience used Claude to guide them through building a home wetlab and sequencing their own genome, highlighting the democratization of DIY biology through AI assistance.