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.
[TRANSFER] Ryzen 9 7900 + Pro B50 GPU VPS
smrgarb
Member
Reselling my Monster KVM-12G + Pro B50 from Hostcram since I'm not using it as much as I thought I would. Specs are:
4x Ryzen 9 7900 Core + Pro B50 GPU
12GB DDR5 RAM + 1.3GB VMEM
120GB NVMe 5.0 Storage
40TB BW @ 10Gbps Port
1 Dedicated IPv4 (Free IPv6)
Got VAAPI and hardware transcoding working properly on it, so if you're after something for transcoding or light AI/inference work it handles that fine. CPU's been solid too, no complaints there.
Asking $340 for the remaining 3 years.
Original listing here for reference: https://lowendtalk.com/discussion/215092/ryzen-7900-arc-pro-b50-gpu-gen-5-nvme-10-gbps-port-salt-lake-city-usa-hostcram-llc/p1
PayPal or crypto works for me, happy to do the transfer whenever you're ready.
This discussion has been closed.
Comments
Sorry $340 USD, I walked away from my desk before I could edit.
It will be good price if 360/36=10$/m
$360 USD for 3 Years (Recurring)
1 Year = 12 months.
∴ 3 Years = 36 months.
$360 USD for 36 months.
$360 USD / 36 Months = $10/month
Yes that is correct. Considering the transfer does not reset expiration and I have owned it for at least a month, I have taken off $10 on top.
I also want it gone hence why I'm happy to take that additional $10 off.
It's a great vps. I have 3 of them combined into 1. A 4th would be nice.... tempting tempting 😜. I've had mine since February and highly recommend it to anyone who picks this up.
Haha 4th time a charm?!
stacking them into a beast
Nah 1gb vram is useless even you spend the 2weeks to make it work
4c12gb for $10 is avg
$42
I dont pay fees
It definitely will work for smaller personal libraries, just didn't fit my use case. Need moar powah
great vps
what do you call light Ai inference ?
Smaller models that can fit on a GPU <1GB. Good for small chat bots :-)
For example, unsloth Qwen2.5 0.5b 4bit QT is roughly 300-400MB in size and can fit up to 64k - 128k token context on this GPU.
https://huggingface.co/unsloth/Qwen2.5-0.5B-bnb-4bit
I have sent you a message.
Sold to @Cashy. Thank you for the seamless transfer :-)
Enjoy!