New on LowEndTalk? Please Register and read our Community Rules.
All new Registrations are manually reviewed and approved, so a short delay after registration may occur before your account becomes active.
All new Registrations are manually reviewed and approved, so a short delay after registration may occur before your account becomes active.
Comments
@hosthatch CM 2024 - AMD Compute 4 GB - T2 in Sydney 🇦🇺
@letbox 1C2G20GB plan in Sydney 🇦🇺
@SmokyHosts non peak times
12GB RAM DDR4
Netcup VPS 1000 G11, EUR 5.75/month on Black Friday 2024
512gb disk is good!
@ComputeBox Which provider?
H4F FR
Great device and rock solid
Rarecloud Germany VPS
Basic System Information:
Uptime : 6 days, 12 hours, 26 minutes
Processor : AMD Ryzen 7 5800X 8-Core Processor
CPU cores : 1 @ 3792.874 MHz
AES-NI : ✔ Enabled
VM-x/AMD-V : ✔ Enabled
RAM : 1.9 GiB
Swap : 1024.0 MiB
Disk : 39.3 GiB
Distro : Ubuntu 24.04 LTS
Kernel : 6.8.0-31-generic
VM Type : KVM
IPv4/IPv6 : ✔ Online / ✔ Online
IPv6 Network Information:
ISP : WIIT AG
ASN : AS24961 WIIT AG
Host : myLoc managed IT AG
Location : Düsseldorf, North Rhine-Westphalia (NW)
Country : Germany
fio Disk Speed Tests (Mixed R/W 50/50) (Partition /dev/vda1):
iperf3 Network Speed Tests (IPv4):
iperf3 Network Speed Tests (IPv6):
Geekbench 6 Benchmark Test:
Test | Value
|
Single Core | 1741
Multi Core | 1768
details please? provider? price?
@nohavps Old LET plan in London 🇬🇧 with Ryzen 9 9950X (with double RAM)
VPS NOHA1 in Frankfurt am Main 🇩🇪 (with double RAM)
@naranjatech €7.5/yr flash sale (thanks to my cumrade @sh97 )
@ComputeBox more details? who provide this? you? url?
Virtono, Hong Kong, 8GB ram, 4 cores, 160GB ssd, 5TB bandwidth (after network repairs)
HostHatch London CM 2024 AMD Compute
Virtono, Hong Kong, 8GB ram, 4 cores, 160GB ssd, 5TB bandwidth (after network repairs, rerun)
@ShockHosting
VPS Singapore
$4.99 / First year -- $29.99 Recurring
RocketCloud 29 ₽/m (like $0.26 USD) (hourly billing) small VM in Moscow 🇷🇺
3$/y 😱 how is the uptime?
EPYC Turin 😍
Host uptime you can see in the YABS
(and is quite a bit more if I didn't reboot the instance a while ago)
Network-wise, same as instance, hasn't gone down.
seems to be a fake. the offer is nowhere to be found.
New provider testing his new hardware? Not yet available. But best advertisement already.
ovhcloud, ks-le-1
Not sure why you think it has to be fake. Not every YABS here is from a deal that you can buy, although most are for obvious reasons.
Many people, including myself, will YABS any new machine we get hold of, including home built and pre-built machines. In these cases, YABS are good as you get an indication of what is achievable from a particular processor and spec combination - even if it's not a "real life provider deal", you can use that to compare against a similar spec machine from a provider to get an idea of how busy the node you're on is, for instance. For this example, it's really useful info to know that this processor can get 2800+ on single core and 5100+ on 2 vCPU.
Of course, this could also be an actual YABS from a provider deal and the poster just forgot to include the deal. Still no reason to accuse it of being fake.
@DigiRDP 1GB Bangalore, $12/y (1 year free in giveaway)
Adding swapfile to re-run GB6 but skip previous tests...
as long as nothing is proven, it's a fake!
Sir, you mean "rigged".
Everything is rigged
But in all seriousness, it's a very new processor with very few results so far.
https://browser.geekbench.com/search?q=AMD+EPYC+9655+96-Core+Processor
Only 2 results to date. This one and one running on all cores: 2837 single core, 22544 multi core. So it's definitely interesting that this YABS was shared, and the single core result suggests this KVM is a representative of performance of a 2vCPU VM on that processor.
EDIT: And it also suggests we might need a GB7 soon, because GB6 multi-core results seem to scale really poorly on any processor with more than about 16 threads.
That's by design. Geekbench 6 is not a full replacement for Geekbench 5. Geekbench 6 is more aimed towards desktop workloads whereas geekbench 5 is better to assess server workloads.
I agree.
GB5 is better indicative of computing power (multicore score) with vCores > 4
I include both GB5 and GB6 in most of YABS.