R
RunPod•2w ago
dave

A4000 - 50GB , BUT ONLY GETTING 16 GB BASED ON nvidia-smi

Hello, not sure if I am doing something wrong, but I purchased a pod using A4000 50GB, but when I run nvidia-smi I only see 16GB. I am not sure why ? I see after purchase that this is 9cpu, so not sure what is going on , since even 9x16 = 144, so why is this advertised as 50GB ? Any clarifications or settings please do advise, it is not obvious.
1 Reply
nerdylive
nerdylive•2w ago
Hey I don't think a4k is 50gbs of vram Are you mistaking video ram and ram? Vcpu is the virtual cores amount what is 9*16? I'm sure you're having the wrong calculations for this, and I think that's not how this works unless you're renting 16 gpus in one pod What were you hoping to rent?
Want results from more Discord servers?
Add your server
More Posts
[URGENT] Failed to return resultsHi, I am having issues for a few hours with one of my serverless pods. When the process ends, it faIs there an equivalent of flash boot for CPU-only serverless?I was trying to figure out if there was a way to have a CPU job only fire up when it was needed so iWhy the available GPUs are only 1?I want to run my pod with at least 2 gpus. My pod is A5000. Now available gpus are ony 2. what happeWhy the available GPUs are only 1?I want to run my pod with at least 2 gpus. My pod is A5000. Now available gpus are ony 2. what happeContacting other site$Is my Pod able to contact other public http or https servers? How do I get the IP address I should oNetwork Blips and pods are not accesisble for some timeIn last 2 days, our 2 pods going off the network and suddenly coming back as if nothing happened.Network Volume Availability on Community Cloud?From all I've read, it looks like Network Volumes are a feature exclusive to the Secure Cloud? If Install ProblemIs it possible, to launch the automatic1111 without calling the full automatic dependancies installeFaster-Whisper worker template is not fully up-to-dateHi, We're using the Faster-Whisper worker (https://github.com/runpod-workers/worker-faster_whisper)Slow IO speeds on serverlessAn A6000 always active worker takes twice as run to run my code than a normal A6000, I think it is I