|
I don't trust youtube as a credible source, and I typically buy starter systems and build on them so I haven't applied that CPU thermal paste to a chip in at least a decade.
The thermal struggle is real with modern PCs and frankly, I trust the bright people here to know more than some rando on youtube.
Getting it wrong might mean cooking hundreds of dollars, so for any of you who do build your own PCs:
I used to apply thermal paste evenly with a credit card, and I'm hearing conflicting things about doing this - do it, don't do it? Nobody can seem to agree.
That suggests either way works, to me, but the cost of being wrong is too much for me to feel comfortable with that.
Anyone here a physics major? 
To err is human. Fortune favors the monsters.
|
|
|
|
|
Evenly does it. Cover the whole die. That's it.
GCS/GE d--(d) s-/+ a C+++ U+++ P-- L+@ E-- W+++ N+ o+ K- w+++ O? M-- V? PS+ PE Y+ PGP t+ 5? X R+++ tv-- b+(+++) DI+++ D++ G e++ h--- r+++ y+++* Weapons extension: ma- k++ F+2 X
|
|
|
|
|
Thanks. That's how I used to do it. I had just read somewhere that it was no bueno, but you know the Internet. 
To err is human. Fortune favors the monsters.
|
|
|
|
|
I know, the ![Elephant | [mastadon]](https://codeproject.global.ssl.fastly.net/script/Forums/Images/elephant.gif) official site for all pharmacies of Italy managed to report as open a pharmacy that was closed and didn't even report the status of an actually open pharmacy 5 km away. Internet: I can know how many back end hairs some k-pop star has but reliable, accurate informations? That's too much.
Anyway, thermal paste is simply a heat conductor, you want heat to go away from the die to the heatsink / cold plate so an even surface gives the best transfer. Just take care near the borders to avoid spilling when you press the plate / sink on the die because the surplus paste may go in places it is not supposed to.
EDIT: for reliable PC building info Jay2Cents and GamerNexus are top quality. Jay2Cents has clickbaity titles but other than that he's honest and knowledgeable. I had to crash course myself back from my last build (2016) and he's been invaluable.
GCS/GE d--(d) s-/+ a C+++ U+++ P-- L+@ E-- W+++ N+ o+ K- w+++ O? M-- V? PS+ PE Y+ PGP t+ 5? X R+++ tv-- b+(+++) DI+++ D++ G e++ h--- r+++ y+++* Weapons extension: ma- k++ F+2 X
|
|
|
|
|
Thanks! That edit is very helpful since it means less bothering you fine people here. I can't help that the community here is pretty reliable. You all make me do this! 
I usually just get starter systems and build on them, but I'm trying to max my single core performance, so I had to go full custom, especially given I'm mATX in a small cubelike form factor, and open air such that liquid isn't a good option.
I have to tread very carefully in general with this build. I've been measuring everything - clearances on my GPU, my CPU, RAM, heatsink, making sure it doesn't overlap the RAM, etc. And I have none of these parts yet, mind you. This is so I don't screw up my huge order, and they all work together.
Bless Noctua. They have heatsink cpu and chassis compatibility databases, and detailed specs. The only thing they don't have in the specs is the relative direction it's supposed to mount and the direction of the airflow but even then you can basically glean that from the marketing material. They've been a huge help, and that alone justifies the price of their gear, which I also hear is excellent in general.
To err is human. Fortune favors the monsters.
|
|
|
|
|
honey the codewitch wrote: Bless Noctua.
I went with be quiet and MSI last time and am very happy. Only manco was the position of one screw, that is unconfortable to get.
M.D.V. 
If something has a solution... Why do we have to worry about?. If it has no solution... For what reason do we have to worry about?
Help me to understand what I'm saying, and I'll explain it better to you
Rating helpful answers is nice, but saying thanks can be even nicer.
|
|
|
|
|
I'm really concerned about keeping my i5-13600K cool on air. I doubt I'll overclock the core much if at all but I might tighten up the RAM timings. My RAM mobo and CPU can all handle it, in theory.
The issue is heat. My case is small, and there have been complaints about heat with this chassis, though I haven't experienced that myself.
Noctua makes the gold standard in air coolers for CPUs. Everybody else compares theirs to Noctua. Their fans are top shelf, and apparently their coolers are designed like the Germans would do it.
NH-D12L[^]
MSI is a good brand but I am not taking any chances with this machine. This cooler is most efficient one I could find that will fit in my case. The only way I'm getting better, AFAIK is going with liquid, which I can't do for reasons.
To err is human. Fortune favors the monsters.
|
|
|
|
|
|
Yes, apply a thin even coat.
|
|
|
|
|
There are many school of thoughts.
some will put a pea size amount in the center and let the cooler spread it out when you screw it down; it works well for smaller CPU size.
other will put it in an X shape and let the cooler spread it out; maybe better for bigger cpu.
others will manually spread it out.
I'm on the X team (I've done it twice in my life,soooo ... )
youdoyou.
CI/CD = Continuous Impediment/Continuous Despair
|
|
|
|
|
Last time I found a place with a nice (and apparently serious) test and explanations about it:
Thermal Paste Application Techniques | Puget Systems[^]
M.D.V.
If something has a solution... Why do we have to worry about?. If it has no solution... For what reason do we have to worry about?
Help me to understand what I'm saying, and I'll explain it better to you
Rating helpful answers is nice, but saying thanks can be even nicer.
|
|
|
|
|
This is from 2012, most CPU at the time would work without a cooler (kinda lol)
I'd like to see a more recent test with a comparable chip (intel 12700 or 13700)
CI/CD = Continuous Impediment/Continuous Despair
|
|
|
|
|
Funny thing is that although the article is dated 2012, the first comment is marked '15 years old' - but it seems to be unrelated to the subject of the article. So something is messed up in the comment system of that site!
To the subject: Do you think that different ways of spreading the thermal paste depends greatly on the CPU model? That the newer chips can benefit from a different way of applying the paste than the chips of ten years ago? Why would that be?
Maybe you are right, that we today should do it in a different way than we did ten years ago, but I do not immediately see any reason for why it would be different today.
After all, that is what the article really is about - not specific temperature measurements of specific CPUs!
(And: You are free to follow the instructions in the article to yourself repeat the tests with 12700 and 13700 and publish the results ).
|
|
|
|
|
the tests has nothing to do with the CPUs.
It is just a plain comparison of different methods of applying the thermal paste, and what happens once you put the cooler on top.
As long as the new CPUs do no have a different surface...
M.D.V. 
If something has a solution... Why do we have to worry about?. If it has no solution... For what reason do we have to worry about?
Help me to understand what I'm saying, and I'll explain it better to you
Rating helpful answers is nice, but saying thanks can be even nicer.
|
|
|
|
|
I did what the instructions with the kit said and it worked.
"Before entering on an understanding, I have meditated for a long time, and have foreseen what might happen. It is not genius which reveals to me suddenly, secretly, what I have to say or to do in a circumstance unexpected by other people; it is reflection, it is meditation." - Napoleon I
|
|
|
|
|
I just put a few drops in the center. Also, my last cooling fan had thermal paste pre-applied on the radiator's contact surface.
There is only one Vera Farmiga and Salma Hayek is her prophet!
Advertise here – minimum three posts per day are guaranteed.
|
|
|
|
|
Don't get it on the contacts - everything will stop working. Ask me how I know.
You can clean it off with white spirit if you do and then start again.
Paul Sanders.
If I had more time, I would have written a shorter letter - Blaise Pascal.
Some of my best work is in the undo buffer.
|
|
|
|
|
Quote: does it matter how I apply it?
Yes
how much does it matter, meh
if it covers the whole cpu, not so much, cpu heats at different points.
that 2012 article posted above, well that simply testing IDLE temp, and how well spread is. well that more about how the contact of the heatsink. bits being missed on the edge already likely to be low heat areas, also if decent test would repeat each multiple times to remove issues with human pushing heat sink on.
unless overclocking to the extreme, drop, or multiple drops tiny, or X if doing thin amounts plus the heatsink push down will contact where heatsink actually contacts. too much will spill out side
too little, will still work, again unless doing extreme 100% load 24/7, ok coverage will be just as good as attempting to get that 1/1000 perfect fit.
|
|
|
|
|
Thanks. This is helpful! I probably won't OC the core frequency and voltages - the thing already runs at 5.1GHz, but I may tighten up the RAM timings (my CPU is unlocked) just to maximize my computing power, but I'm not going to get too crazy with OC anyway since I'm on air. That said, my air setup should handle some amount of OC.
To err is human. Fortune favors the monsters.
|
|
|
|
|
Are you sure it isn't already applied? Most heatsinks now will already have a thin layer applied to them and you just push it on carefully.
But if not, I've always just put a blob in the middle and let it push out.
|
|
|
|
|
I'm not sure yet. I considered that, but I haven't ordered the parts yet. I'm pulling the trigger on everything all in one shot in December after a contract pays out. I just want to have my ducks in a row for when everything gets here so I've been covering all my angles - cooling, wattage, clearances, etc and this has always been part of it for me, so I wanted to get good info on it. I started searching online and saw a bunch of conflicting information as I said, so here I am.
To err is human. Fortune favors the monsters.
|
|
|
|
|
Well if you go for any of the Corsair all in one liquid coolers(which I would recommend) then it would already have thermal paste applied.
|
|
|
|
|
My chassis is a thermaltake Level 20 VT, and while it's set up in theory to take either air or liquid, it's partially an open air chassis - it's enclosed, but there are gaps between the glass panels and chassis itself.
These require positive air pressure, which in turn requires 4 120mm fans mounted on top of my case blowing about 1cm away from the glass to push positive pressure over the edges of it.
It has kept dust and cat hair out for a year so far. I am loath to change it, and installing a radiator means ditching those fans for lack of space. At that point I lose the positive air pressure along one side, and potentially create a vacuum point for dust. Not a fan of that.
To err is human. Fortune favors the monsters.
|
|
|
|
|
Pea size dot on the die, if the die is square. Smuch the pea.
Rectangular requires a small line.
This is to avoid air bubbles, which you occasionally get when doing patterns like x's or such. In the ideal world, you'd want an even spread and as little paste as necessary, hence the pea comparrison for reference on what "little" means in this context.
Not much you can do wrong really.
|
|
|
|
|
Kate-X257 wrote: In the ideal world, you'd want an even spread and as little paste as necessary
That's why historically I've used the credit card approach - applying it and then using a credit card to smooth and thin it across the entire surface.
To err is human. Fortune favors the monsters.
|
|
|
|
General 
News 
Suggestion 
Question 
Bug 
Answer 
Joke 
Praise 
Rant 
Admin 
Submit an article or tip
