Mac Studio again, this time working with SD input resolution. 10% max vram followed by 100%. Notice that every result is faster when set to 10%…
Topaz Video AI v3.1.10
System Information
OS: Mac v13.0201
CPU: Apple M1 Max 32 GB
GPU: Apple M1 Max 21.333 GB
Processing Settings: device: 0 vram: 0.1 instances: 1
Input Resolution: 720x480
Benchmark Results
Artemis 1X: 33.1 fps 2X: 22.17 fps 4X: 8.67 fps
Proteus 1X: 33.76 fps 2X: 23.11 fps 4X: 8.02 fps
Gaia 1X: 10.91 fps 2X: 7.7 fps 4X: 6.27 fps
4X Slowmo Apollo: 27.94 fps Chronos: 11.68 fps Chronos Fast: 15.91 fps
Topaz Video AI v3.1.10
System Information
OS: Mac v13.0201
CPU: Apple M1 Max 32 GB
GPU: Apple M1 Max 21.333 GB
Processing Settings: device: 0 vram: 1 instances: 1
Input Resolution: 720x480
Benchmark Results
Artemis 1X: 24.16 fps 2X: 15.38 fps 4X: 5.62 fps
Proteus 1X: 23.72 fps 2X: 14.44 fps 4X: 5.07 fps
Gaia 1X: 7.69 fps 2X: 5.79 fps 4X: 4.66 fps
4X Slowmo Apollo: 27.32 fps Chronos: 8.25 fps Chronos Fast: 11.19 fps
1 Like
Imo
March 24, 2023, 7:21am
100
v.3.1.9 is still the fastest for me. The v.3.2.0.4.a is slightly faster than the v.3.2.0.3.a.
TPX
March 24, 2023, 8:39am
101
The numbers for the 4090 are sureal (7950X), 40 fps for artemis in the alpha.
2 Likes
Imo
March 24, 2023, 11:47am
102
v.3.2.0.4.a / the whole windows 11 froze during processing. v.3.1.9 ran rock solid for a whole day whithout any pause.
johnnystar
March 25, 2023, 1:51pm
103
Mine is the fastest at exactly 0.93 VRAM.
DaveL
March 25, 2023, 5:51pm
104
Quoted from the releases 3.1.10 thread >>
Hoping to get some more love for AMD, AV1 option still not enabled for 7900 xtx unfortunately. I posted the most relevant benchmarks for the typical all AMD build. Also nice to see that the 7900 xtx perform similar to the RTX 4090
Topaz Video AI v3.1.10
System Information
OS: Windows v11.2009
CPU: AMD Ryzen 9 7950X 16-Core Processor 31.146 GB
GPU: AMD Radeon RX 7900 XTX 23.945 GB
GPU: AMD Radeon(TM) Graphics 0.47446 GB
Processing Settings: device: 0 vram: 1 instances: 1
Input Resolution: 640x480
Benchmark Results
Artemis 1X: 65.22 fps 2X: 23.67 fps 4X: 7.13 fps
Proteus 1X: 43.3 fps 2X: 24.1 fps 4X: 8.17 fps
Gaia 1X: 47.82 fps 2X: 33.92 fps 4X: 18.75 fps
4X Slowmo Apollo: 119.97 fps Chronos: 43.39 fps Chronos Fast: 78.8 fps
XTX stats are excellent for the price, but are closer to (but better than) the RTX 3060 TI actually, which is of course well under half the XTX price and around 25% of the 4090 price. At SD resolutions, my benchmarks for the 3060 TI are mostly faster than the XTX. I’m now off to find some SD benchmarks posted for the 4090
The odd thing is that there are wild variations between some of the models’ performances - my 3060 TI performs badly on Gaia and one or two others, but mostly very well.
Topaz Video AI v3.1.10Input Resolution: 1920x1080
Topaz Video AI v3.1.10Input Resolution: 640x480
The law of diminishing returns certainly applies here for me, because I use Artemis or Proteus for 2x upscales and Apollo or Chronos Fast for slomo. And if I upgrade the GPU in my existing no. 2 PC to a 3060 TI (making 2 systems with 3060 TI), I can get more throughput at 1080p or below than a single 4090, for 25% of the price of a single 4090 upgrade.
These benchmark tables are a brilliant help in choosing what to do!
1 Like
Hello there,
My benchmark results
Topaz Video AI v3.1.1012th Gen Intel(R) Core™ i7-12700K 31.789 GBNVIDIA GeForce RTX 3070 Ti 7.8428 GB
Input Resolution: 1920x1080 11.49 fps 2X: 5.04 fps 4X: 1.42 fps 8.9 fps 2X: 4.79 fps 4X: 1.39 fps 5.11 fps 2X: 3.3 fps 4X: 1.83 fps 13.38 fps Chronos: 10.83 fps Chronos Fast: 15.26 fps
Input Resolution: 720x480 77.4 fps 2X: 33.48 fps 4X: 8.1 fps 63.65 fps 2X: 27.65 fps 4X: 8.18 fps 28.77 fps 2X: 19.81 fps 4X: 11.41 fps 74.74 fps Chronos: 56.27 fps Chronos Fast: 75.02 fps
Input Resolution: 640x480 80.19 fps 2X: 31.05 fps 4X: 8.37 fps 62.72 fps 2X: 27.94 fps 4X: 7.95 fps 29.05 fps 2X: 20.19 fps 4X: 11.76 fps 72.93 fps Chronos: 57.39 fps Chronos Fast: 73.1 fps
1 Like
I look forward to you guys optimizing the app to leverage AMD cards better. A 7900 XTX is on-par with a 4080 (if you leave out raytracing) but in Topaz I am getting almost half the speed that people with a 4080 are getting. LOTS of room to improve for sure!
What is odd, is that my single 7900 XTX is listed twice? I tried to set settings to use ALL GPUs so it might leverage my iGPU integrated on the AMD 7900X CPU, but when I do that it actually runs slower.
Single Processor Setting:
Topaz Video AI v3.1.10
System Information
OS: Windows v11.2009
CPU: AMD Ryzen 9 7900X 12-Core Processor 31.118 GB
GPU: AMD Radeon RX 7900 XTX 23.945 GB
GPU: AMD Radeon(TM) Graphics 0.47446 GB
GPU: AMD Radeon RX 7900 XTX 23.945 GB
Processing Settings: device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 9.52 fps 2X: 5.03 fps 4X: 1.48 fps
Proteus 1X: 7.63 fps 2X: 4.28 fps 4X: 1.6 fps
Gaia 1X: 6.79 fps 2X: 4.37 fps 4X: 2.91 fps
4X Slowmo Apollo: 18.33 fps Chronos: 9.29 fps Chronos Fast: 10.06 fps
ALL GPUs:
Topaz Video AI v3.1.10
System Information
OS: Windows v11.2009
CPU: AMD Ryzen 9 7900X 12-Core Processor 31.118 GB
GPU: AMD Radeon RX 7900 XTX 23.945 GB
GPU: AMD Radeon(TM) Graphics 0.47446 GB
GPU: AMD Radeon RX 7900 XTX 23.945 GB
Processing Settings: device: 3 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 2.21 fps 2X: 1.63 fps 4X: 1.27 fps
Proteus 1X: 7.07 fps 2X: 1.93 fps 4X: 0.81 fps
Gaia 1X: 7.13 fps 2X: 2.4 fps 4X: 0.89 fps
4X Slowmo Apollo: 6.24 fps Chronos: 2.84 fps Chronos Fast: 0.43 fps
V3.1.11 and latest Nvidia Studio driver 531.41
Topaz Video AI v3.1.11
System Information
OS: Windows v10.2009
CPU: AMD Ryzen 5 3600 6-Core Processor 15.927 GB
GPU: NVIDIA GeForce RTX 3060 11.84 GB
Processing Settings: device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 8.11 fps 2X: 4.53 fps 4X: 1.3 fps
Proteus 1X: 7.76 fps 2X: 4.35 fps 4X: 1.3 fps
Gaia 1X: 3.15 fps 2X: 2.1 fps 4X: 1.26 fps
4X Slowmo Apollo: 9.89 fps Chronos: 6.94 fps Chronos Fast: 10.22 fps
ole.solev
March 29, 2023, 7:04am
108
ALL GPUs - disable in bios GPU inside CPU
Topaz Video AI v3.1.10
System Information
OS: Windows v11.2009
CPU: AMD Ryzen 9 5900X 12-Core Processor 31.924 GB
GPU: NVIDIA GeForce RTX 2070 SUPER 7.8154 GB
Processing Settings: device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 11.28 fps 2X: 6.29 fps 4X: 1.73 fps
Proteus 1X: 10.62 fps 2X: 6.05 fps 4X: 1.78 fps
Gaia 1X: 3.89 fps 2X: 2.57 fps 4X: 1.65 fps
4X Slowmo Apollo: 8.56 fps Chronos: 3.48 fps Chronos Fast: 12.98 fps
Looks like my ageing RTX 2070 Super still holds up pretty well, not bad at all.
1 Like
Topaz Video AI v3.1.11
Processing Settings: device: 0 vram: 1 instances: 0
Processing Settings: device: 0 vram: 0.8 instances: 0
Input Resolution: 1280x720
Benchmark Results
Artemis 1X: 18.51 fps 2X: 11.33 fps 4X: 3.41 fps
Proteus 1X: 17.34 fps 2X: 11.26 fps 4X: 3.43 fps
Gaia 1X: 6.29 fps 2X: 4.41 fps 4X: 2.9 fps
4X Slowmo Apollo: 16.54 fps Chronos: 13.27 fps Chronos Fast: 18.29 fps
Processing Settings: device: 0 vram: 0.6 instances: 0
Processing Settings: device: 0 vram: 0.1 instances: 0
Input Resolution: 1280x720
Benchmark Results
Artemis 1X: 9.48 fps 2X: 6.45 fps 4X: 2.2 fps
Proteus 1X: 8.62 fps 2X: 6.03 fps 4X: 2.18 fps
Gaia 1X: 3.28 fps 2X: 2.33 fps 4X: 1.59 fps
4X Slowmo Apollo: 15.72 fps Chronos: 6.49 fps Chronos Fast: 16.52 fps
Topaz Video AI v3.1.11
System Information
OS: Windows v11.2009
CPU: AMD Ryzen 7 5800X 8-Core Processor 31.915 GB
GPU: NVIDIA GeForce RTX 3060 11.845 GB
Processing Settings: device: 0 vram: 1 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 8.54 fps 2X: 5.12 fps 4X: 1.59 fps
Proteus 1X: 8.17 fps 2X: 5.24 fps 4X: 1.57 fps
Gaia 1X: 2.89 fps 2X: 1.99 fps 4X: 1.31 fps
4X Slowmo Apollo: 7.45 fps Chronos: 6.38 fps Chronos Fast: 10.16 fps
Processing Settings: device: 0 vram: 0.8 instances: 0
Processing Settings: device: 0 vram: 0.6 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 8.1 fps 2X: 5.23 fps 4X: 1.56 fps
Proteus 1X: 7.39 fps 2X: 4.76 fps 4X: 1.57 fps
Gaia 1X: 2.59 fps 2X: 1.78 fps 4X: 1.15 fps
4X Slowmo Apollo: 8.02 fps Chronos: 5.79 fps Chronos Fast: 9.96 fps
Processing Settings: device: 0 vram: 0.1 instances: 0
Topaz Video AI Alpha v3.2.0.4.a
DaveL
March 30, 2023, 2:14pm
111
Has anyone benchmarked two equivalent GPUs in the same computer?
I notice that a few of the reported benchmarks in this thread report two identical GPUs but comments suggest that this is the benchmark falsely reporting two, when there is only one (of the same type).
If anyone is able to post comparative benchmarks with one then both equivalent GPUs enabled that would help others including me to decide on the most cost-effective way to upgrade. Specifically, while still available, I could upgrade my one 3060 ti to two of them - if the performance impovement would be worthwhile (but benchmarks of any doubled-up GPU will help to decide)…
There was one post on the version topic, I think, they posted benchmark results form a crazy system with an AMD Epyc CPU with like 96 cores or something. I think they had 4 GPUs in it.
Anyway, to me it seems like if you have enough CPU cores, another GPU will help a lot. You’ve got the Ryzen 7950X, that’s 16 cores. I think you’d benefit from another RTX 3060 ti. What don’t think you will get is faster speeds processing one video. I suppose that’s what your asking for though: Will the All GPU setting use all the GPUs and get double the speed? I think it’s safe to say you would be able to process at least two videos at the same time with no speed decrease.
DaveL
March 30, 2023, 3:50pm
113
Yes that’s what I’m wondering, thanks for the comments. The choice is 1) upgrade my no. 2 system from 1070 to 3060 ti (I’ve already tested by borrowing it from my newer system and speeds are similar) or 2) add a 2nd. GPU to my newer system, which would be more convenient if the overall result is similar (approaching twice the output). There’s plenty of spare capacity in the CPU. I may have to upgrade the PSU though.
This is all because I can’t justify the expense of upgrading to a 4080 or 4090 unless it would double the processing speeds on 1080p or lower resolutions, and posted benchmarks indicate that they would not. If I go ahead, I will of course post the comparative benchmarks in here.
What does the “device” setting indicate in the benchmark tool?
It represents the “AI Processor” setting in the TVAI preferences. I think 0 is usually (if not always) the GPU.
Thanks.
Andy
Topaz Video AI v3.1.11
System Information
OS: Mac v12.0604
CPU: Apple M1 Pro 16 GB
GPU: Apple M1 Pro 10.667 GB
Processing Settings: device: 0 vram: 0.9 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 5.37 fps 2X: 3.47 fps 4X: 0.76 fps
Proteus 1X: 5.75 fps 2X: 3.29 fps 4X: 0.83 fps
Gaia 1X: 1.91 fps 2X: 1.4 fps 4X: 1.08 fps
4X Slowmo Apollo: 3.85 fps Chronos: 1.79 fps Chronos Fast: 2.9 fps
Topaz Video AI v3.1.11
System Information
OS: Mac v12.0604
CPU: Apple M1 Pro 16 GB
GPU: Apple M1 Pro 10.667 GB
Processing Settings: device: 0 vram: 0.9 instances: 1
Input Resolution: 640x480
Benchmark Results
Artemis 1X: 23.55 fps 2X: 12.31 fps 4X: 5.05 fps
Proteus 1X: 23.55 fps 2X: 11.25 fps 4X: 4.53 fps
Gaia 1X: 7.55 fps 2X: 5.69 fps 4X: 4.58 fps
4X Slowmo Apollo: 24.12 fps Chronos: 7.81 fps Chronos Fast: 11.42 fps
rfrankway
March 31, 2023, 3:44pm
118
Both of these are fresh boots with no other applications running:
Topaz Video AI v3.1.11
System Information
OS: Mac v13.03
CPU: Apple M2 Max 96 GB
GPU: Apple M2 Max 72 GB
Processing Settings: device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 10.45 fps 2X: 7.38 fps 4X: 2.43 fps
Proteus 1X: 11.51 fps 2X: 7.18 fps 4X: 2.19 fps
Gaia 1X: 3.41 fps 2X: 2.52 fps 4X: 1.95 fps
4X Slowmo Apollo: 11.07 fps Chronos: 3.39 fps Chronos Fast: 5.35 fps
Topaz Video AI v3.1.11
System Information
OS: Windows v11.2009
CPU: AMD Ryzen 9 3950X 16-Core Processor 31.923 GB
GPU: NVIDIA GeForce RTX 2080 Ti 10.782 GB
GPU: NVIDIA GeForce RTX 2080 Ti 10.782 GB
Processing Settings: device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 14.96 fps 2X: 6.67 fps 4X: 1.93 fps
Proteus 1X: 12.68 fps 2X: 6.53 fps 4X: 1.88 fps
Gaia 1X: 5.35 fps 2X: 3.54 fps 4X: 2.12 fps
4X Slowmo Apollo: 12.08 fps Chronos: 4.48 fps Chronos Fast: 16.92 fps
