Last week one of the $70 or $75 sellers would only go down to $69 each through best offer. I tried I think around 60-65 and they said no. I declined for 69 and kept hunting with other sellers. They were in the $80-90s probably around a month ago though and keep adding more inventory as they sell so not sure how many they actually have in total. If they sold 50ish in the last day or two I wouldn’t suspect them to go much lower.
1 Like
I may have gone slightly overboard buying 8. Lmao
Now I need to setup a system that can handle 8 cards. I was thinking a 7002 epyc system but I only saw ones with 6 pcie slots so far. But 128GB of video ram total of I pull it off
I was going to do just 6 just the seller had 8 left and I figured they would go lower if I got rid of all they had left.
1 Like
Btw liquid metal’ing these is totally worth it, but be sure to use conformal coating on the capacitor s around the dies
2 Likes
Hey, has anyone had a chance to look at the PCB of this thing? How much like the WX9100 or Vega FE is the board? If its the same pcb, we might just be able to figure out which pins are outputting video on the FE bios and solder on a display port to get video out.
The first 4 at the top might get it working but one of them is HDMI on Vega FE so maybe only up to 3 displays, you also need little capacitors and resistors
To my knowledge it’s pretty much the same as a wx9100 pcb
There is already a mini-DP on there, and you can just flash the WX9100 vbios to enable it. Is that what you were wondering about, or are you talking about enabling the other 5, unpopulated mini-DP outputs?
I am talking about having a way of having the higher power limit and video output.
The easiest way to do that is to flash the WX9100 vbios and then apply the Vega 64 PP table in software. That process is also documented in the thread I linked:
Just Ordered the Radeon Pro V540 for $160, i wonder how it will compare to the MI25!
Uhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhh
Those don’t have drivers yet since their engineering samples
The boot camp team is working on windows drivers
ah. we do have V520s at work, so i wonder if the drivers work, since they are just a dual GPU version of that no?
If you get your hands on that driver message me, I also have a v540
Will do 
I see now, thats actually pretty cool. TY : )
I am thinking about getting an MI25 - I used to own a few VEGA 64 LC Models and simply loved the HBM and FP16 Compute vapabilities back then (still having a FURY X with HBM lying around).
Since I have a 3060 12GB and an ARC 770 16GB currently in the system - I was wondering what the speed differences to a MI25 would look licke. But its not easy to find comparable numbers which are reliable… There are a lot of tests done indivudally but almost every test is either using different paramters, frameworks, sometimes its a DirecML Implementation… And the results are all over the place.
What I found so far is that ARC is not fully supported, so here still is room for improvmement - but Nvidia is well suported for stable diffusion and RTX Cards with tensor cores do outperform VEGA Architecture Cards easily in other inference tasks. I had this experience with upscaling or video interpolation inferences - as long as the Tensor cores were not in the game, the VEGA crushed a lot of mid range RTX GEN 20 and 30 cards - but as soon as development progressed and the backends fully supported the Tensor cores - the VEGAs fell behind.
Did anybody benchmark the Mi25 against a 3060?
So RTX series cards have tensor cores for acceleration, so even without doing the benchmarking its already the winner, the cycle diffrence is night and day basicly.
Also your correct about the software support on Intel and if you haven’t seen the benchmarks, this is a good point in time measurement.
Thanx,
I figured that RTX Cards would be ahead. I am wondering what the price/performance ratio would be:
comparing one used RTX 3060 vs two MI25 for around the same price - which one would come out ahead in stable diffusioN ?
Have a review of the numbers here
Thanx for replying.
Thats what I was refering to… These Benchmarks only show numbers of the VEGA Architecture. Odly, the FP16 Numbers on the MI25 are slower than the FP32 ones - VEGA 10 has rapid packed math, the FP16 numbers should not only show lower VRAM usage (which the do), but also give faster runtimes (which they don´t).
The comparison then shows a MI210 and then continues to a A6000 with no numbers in the chart .
Thats why I wrote I had a hard time finding reliable benchmark numbers. Of course I read a whole bunch of reddut posts (most of them refering this post and tom´s hardware bench), the tom´s hardware article/bench (which lacks vega64 numbers and is using lower batch sizes)…
Bottom Line: IF a RTX3060 would come out clearly ahead of the MI25 and 12GB are enough for most cases - why bother about the MI25 (aside from 16GB which might help in some cases and the fact that its a fun project).
I love these kind of projects, i had several M40s, K10, K80, S7150, S9xx… and always had a lot of fun turning them into something usefull, 3d printing fan shrouds, modding bioses…
But here I am a little puzzeld - the numbers which I can gather from the web seem to indicate that an RTX 3060 is way ahead of a MI25 … BUT: The numvbers are all from different scnearios - one was using smaller resolutions, the next one ran Linux, etc…
So to clear this up - I was looking for a clear, reliable benchmark, comparing the 3060 to a MI25 in this scenario (other benchmarks are not comparable - i know that pure shader performance of a VEGA10 chip in FP16 scalar shader loads is ahead of a rtx 3060)…
Various user submitted benchmarks here
And also here
1 Like