惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

博客园 - 叶小钗
Last Week in AI
Last Week in AI
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
雷峰网
雷峰网
GbyAI
GbyAI
Hugging Face - Blog
Hugging Face - Blog
N
Netflix TechBlog - Medium
博客园 - 聂微东
Y
Y Combinator Blog
罗磊的独立博客
博客园_首页
小众软件
小众软件
有赞技术团队
有赞技术团队
爱范儿
爱范儿
F
Fortinet All Blogs
C
Check Point Blog
Google DeepMind News
Google DeepMind News
云风的 BLOG
云风的 BLOG
Apple Machine Learning Research
Apple Machine Learning Research
M
MIT News - Artificial intelligence
月光博客
月光博客
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
博客园 - 司徒正美
aimingoo的专栏
aimingoo的专栏

Proxmox Support Forum

[SOLVED] - Github Auth for Mirrors-Kernel Repo? [Automation] Mass migration tool for MS Win11/Server Proxmox GUI hang - not response is it possible to reject or quarantine spam based on conditions I set ? The PVENode task list in PVE9 is partially obscured due to the terminal font being too large. About 100% error reporting due to pveproxy.service hooks Kubernetes overlay networking breaks when upgrading from PVE 9.1 to PVE 9.2.3 Zentraler Speicher No space left on device Combine datastore and direct file archival to tape Kernel panic VFS: Unable to mount root fs on unknown-block (0,0) sobald ein 7.x Kernel verwendet wird. How to migrate disk of a VM from one ZFS to another Windows Server 2025 fails to boot after PVE 9.2 / Linux 7.0 Kernel upgrade Cannot Install Proxmox on T610 Poweredge with H700 PERC card sdn Config. gateway not reachable How to safely change domain/FQDN? Welche Filterquote erreicht ihr? NFS Share status unknown on 2 of 5 nodes Can't connect to PVE9 consoles [solved] Can't connect to PVE9 consoles [solved] [SOLVED] - Use secondary network for PVE commands Created cluster, one node storage gone BUG: proxmox mail gateway FROM = null bypass spam filtering Moving existing PBS from VMWare workstation to PVE cluster Does eBGP SDN fabric support external peering? Bug: PDM 1.1 not recognizing valid license status Proxmox GUI hang - not response PVE crashes unexpectedly Proxmox Backup Server 4.2 released! Advice
Suggesting for Low power Mini PC
invalid@exam · 2025-09-13 · via Proxmox Support Forum

Late to this, but the "low power" half of the ask never got answered with actual numbers, and that is exactly where 8-core AMD mini PCs trip people up, so here are measured idle figures for the boxes in play.
Idle on these tracks the AMD generation, not the core count, and it swings about 5x:
Beelink SER5 Pro (Ryzen 7 5800H, 8C/16T): ~5.3-8.2 W idle, takes 64 GB DDR4. Andrew's pick is genuinely one of the lowest-idle 8-core boxes going, so it is a good steer for your priority.
Aoostar R7 (Ryzen 7 5700U, 8C): ~7.3 W idle, but 32 GB max.
Minisforum UM690 (Ryzen 9 6900HX, 8C): ~8-10 W idle, 64 GB.
Beelink SER8 (Ryzen 7 8845HS, 8C): ~7-10 W idle (package 3.5-4.7 W) if you want a newer chip.
The catch: newer is not lower here. A SER6 Pro (7735HS) measures 20-35 W idle and a UM790 Pro (7940HS) 25-45 W, so reaching for the latest Zen4 HS chip can triple your standby draw versus the 5800H. On an always-on box at UK rates (~£2-2.50 per watt per year) that gap is most of your running cost.
On the EliteDesk 805 G8 idea, nothing wrong with a validated big-name box, just note the AMD Pro mini line tends to ship Realtek 1GbE NICs (the 705 G4 and Lenovo M75q both do), which are fine under Proxmox/Debian but not under ESXi if that ever matters. I do not have a clean measured idle number for the 805 G8 specifically, so I will not invent one.
On dropping your existing Proxmox SSD straight into new hardware: it usually boots since it is just Debian, but two things bite. The NIC comes up under a different name on the new board, so vmbr0 loses its uplink until you fix /etc/network/interfaces. And you are on Legacy BIOS now, so a UEFI-only box means repairing the bootloader. Doable, just not always plug-and-play, so pringlestuffs' caution is fair.
One extra if you ever want iGPU passthrough for transcoding: the Ryzen APUs (680M/780M) hit the AMD reset bug where the GPU only resets once per host power-on. The older 5800H Vega is less affected than the 680M. Ignore this if passthrough is not in the plan.
Full disclosure, I built a small free thing for exactly this decision because I got tired of re-deriving measured idle / NIC chipset / passthrough notes per box from scattered reviews: https://idlewatt.vercel.app (every figure cited to a wall-meter source, data is CC-BY at https://github.com/SolvoHQ/homelab-mini-pc-dataset). Corrections welcome if your SER5 idles differently from what is listed.