The stuff Hacker News actually recommends.

GPUs and CPUs · AMD Ryzen 9

AMD Ryzen 9 7950X

18owners with an opinion
67%of verdicts positive
8/4positive/negative since 2024
0happy after 3+ years

Praised for performance and noise; criticized for reliability.

What owners wrote

NeutralOwned 2 years
I noticed the comments pointing out that TDP is a marketing number, and max power draw for this part can be higher. The cooling seems to have been inadequate. A rule of thumb I use for cooling is, you can rarely have too much. You should over-engineer that aspect of your systems. That and the power supply. I have a 7950x, with a water block capable of sinking up to 300W. Under heavy load, I hear the radiator fans spinning up, and I see the cpu temp hover around 90-93 C. That is ok, though cooler would be better. My next build (this one is 2 years old) will also use a water block, but with a higher flow rate, and a better radiator system. I like silent systems, though I don't like the magic smoke being released from components.
Likes it
Openrouter is not ideal, because you don't know who they send your traffic to and there are rumours of vendors cheating by providing quantized models. I'm very happy with Deepinfra. Less model coverage, but good prices and quite fast. However I have to caution you about one thing. No one will give you as many input tokens for so little money as Claude Max x5 (maybe x20 too, I use x5). I tend to use 1.1B to 1.4B a week about 0.8-1B cached. Even with cache were talking thousands of $ in API prices a week. Hundreds if we're talking cheap cloud like Deepinfra. However, local AI well setup is actually a good alternative for this if Claude Max was unavailable. For example my system a ryzen 7950x 192GB ram, 5x rtx3090 plus an rtx5060 ti 16gb. (3 rtx3090 cards via usb4 egpu dock). Let's me run Qwen3.8-Flash-Next with 3slots (no rtx5060 used) at 55tok/s decode dropping to 50 at the end of a 260k context, 1200tok/s refill dropping to 950 at the end of context. With RAM and ssd cashing and 80% cache were talking on the order of 4B a week could be ingested by this setup (roughly) if it was running 24/7. I found 6 interactive cloud code sessions are fairly pleasant with this 3 user setup. If I include the rtx5060 in the mix I can bump to 5 users, but it slows down by about 15% (note the speeds are give are for one active user, multiple users at once see maybe 70% of tgat per user so aggregate is much higher in multi user setup). So in theory I should be able to run 10 cloud code sessions…
Neutral
The last 20% of the performance takes like >75% of the power with Zen 4 systems XD. A Ryzen 9 7945HX mini pc I have achieves like ~80% of the all-core performance at 55W of my Ryzen 9 7950X desktop, which uses 225W for the CPU (admittedly, the defaults). I think limiting the desktop CPU to 105W only dropped the performance by 10%. I haven't done that test in awhile because I was having some stability problems I couldn't be bothered to diagnose.
Likes it
I built my current computer last fall. The Ryzen 7950X was on an awesome sale for black Friday and after looking at the math buying a 9950X just didn’t make sense. So I got the 7950X and 96GB of DDR5 RAM (2 sticks, so I can double later if I need to). Loving it, it was the perfect choice. All this to say some people do in fact do this ;)
Likes it
I have the 7950x, and if I set it to 65W eco mode, I still have basically the same geekbench score 65W: https://browser.geekbench.com/v6/cpu/6126001 105W: https://browser.geekbench.com/v6/cpu/5821065 I actually haven't tested it with 170W (which is the default for the 7950x) for whatever reason, but the average 7950x score on geekbench is basically the same as my geekbench scores with lower than normal TDP. https://browser.geekbench.com/processors/amd-ryzen-9-7950x I wouldn't be surprised if the same is possible with the newer CPUs. Nice added bonus is that my PC fans barely spin (not at audible speeds)
Likes it
Same, I have a Ryzen 9 7950X and it has 130-140% better performance (according to Geekbench) https://browser.geekbench.com/v6/cpu/compare/8593555?baselin... Though a MacBook Pro 16" with M4 Max(that's what achieved this geekbench score), but the same amount of memory (64GB) and the same amount of storage (4TB) as my PC, would cost 6079€. That is roughly twice as much as my whole PC Build did cost, and I'm able to expand Storage and upgrade my CPU and GPU in the future (for way less than buying a new Mac in a few years)
Neutral
Desktop Ryzen 7950X. Increasing the VRAM size (UMA size) to 4 GB fixed the frequent driver timeouts for me. Reverting to older driver (driver cleaner -> driver v23.11.1) fixed the memory leak. This memory leak is weird since PoolMon doesn't show anything unusual. Nothing shows as using too much memory anywhere, except committed memory size grows to over 100GB after few days of uptime and RamMap shows a large amount of unused-active memory.
Likes it
Well... I wanted a dedicated AI/ML box here at home, with enough horsepower to do some interesting AI stuff (but without breaking the bank totally). So I built myself a new PC from parts for the first time in around 20 years. That was ... interesting. Building a PC is - in many ways - not that different than it was in 2005. But it's also changed in many ways. So I spent a lot of time researching and picking out parts, and then building the system. Which led me to things like spending hours watching youtube videos on "What's the best thermal paste" and "what's the best CPU cooler" and "are thermal pads better or worse than thermal paste" and "Do you need one of these CPU gasket things if you're running socket AM5" and so on. I just got the box finished up over the weekend and it's working really nicely so far. I went with an MSI MEG x670e "Godlike" motherboard, AMD Ryzen 9 7950X CPU, MSI Gaming Radeon RX 7900 XTX GPU, and 64GB of DDR5 RAM. The whole thing is running Ubuntu 22.04 (I was going to use Alma Linux, but the Alma installer wouldn't even start), ROCm 6.1.0 and Ollama. So far I've mostly been working with the LLM stuff using Ollama and the llama3 model. Now I've started using Spring AI to interface with the Ollama API. Next steps: figure out "function calling" with Ollama (which doesn't seem to be supported by Spring AI yet, boo) and some "agentic workflows" and multi-agent stuff...
Neutral
I would use ECC memory if I could. I used to use a TR 2920x with ECC but now I'm on a Ryzen 7950x with non-ECC. Unbuffered ECC memory is the only one supported by Ryzen, and it's slower or more expensive or both compared to the equivalent-capacity non-ECC memory. The latest Threadripper lineup supports Registered ECC, but Threadripper is overkill (cost, threads, PCIe lanes) for home users like myself.
Likes it
For me it's about having a silent PC and not making the room feel like a sauna. I have a Ryzen 7950X in ECO mode 105W that's very fast in every workload I can throw at it, trivial to run whisper quiet with a basic Noctua cooler, and barely warms the room.
Likes it
Yes, exactly. Modern chips thermal throttle by default, their turbo clocks/voltages aren't sustainable with most cooling solutions, so, reducing the voltage the chip runs at lowers the power consumed and allows the chip to maintain a higher clock for longer durations. There is, of course, a risk that the lower voltage won't be stable, but, as long as you stress test your system as you would while overclocking, you'll be able to find a lower voltage that is workable. The 7000 series ryzen chips have this built into most motherboard bioses by the name 'pbo offset' (or similar) which modifies the stock voltage curve lower, and can set new temperature targets if desired. I'm running my 7950x at PBO level 3 with an 85c target, works well with no more fuss than a couple reboots really.
Neutral
Using TheBloke nous-hermes-2-mixtral-8x7b-dpo.Q5_K_M.gguf, llam.cpp with oobabooga, on Ryzen 9 7950x and RTX 2070 super, offloading 4 layers to the GPU. 27,631MiB system memory used. 7358/8192MiB usage on the GPU. I'm getting 6.32 tokens/second. You: You are Hunter S. Thompson, write a 450 words essay on the LHC project. The writing must be in Thompson's style AI: Well, buckle up, kiddos, because we're about to dive into the twisted world of particle physics and the Large Hadron Collider, or as I like to call it, the Doomsday Machine. This beast of a thing is buried deep beneath the Swiss countryside, a 17-mile-long ring of death and destruction that makes the atom bomb look like a goddamn firecracker. Now, let me tell you, when the Swiss government first proposed this monstrosity, I thought they'd gone completely batshit crazy. But then again, this is the land of Toblerone and Heidi, so maybe I shouldn't be too surprised. The LHC is essentially a giant, underground racetrack for subatomic particles, where they're accelerated to nearly the speed of light before being smashed into each other like a couple of drunken frat boys at a kegger. The goal of this madness? To recreate the conditions that existed just after the Big Bang, when the universe was nothing more than a seething cauldron of energy and chaos. And if that doesn't sound like a recipe for disaster, I don't know what does. But let's not forget the real reason we're all here: the Higgs boson, or as it's more commonly…
Neutral
7950x with 4x32GB @ 3800MHz here. Getting similar results except my single thread performance is the worst (around 40), otherwise it looks almost identical. I assume my poor single thread perf is due to having capped max CPU core clock at 4.5Ghz. Getting 4 sticks to boot was a pain, haven't really bothered to change anything once I finally got it running stable.
Likes it
>The computers of yesteryear had this little feature known as blinking LED lights .They also had this other feature called noisy disks and loud fans You just described my reasonably current water-cooled PC (except the disks - it only uses SSDs). I have a direct die water-cooled ryzen 7950x and 2x 3090 gpus. Normally my PC is completely silent. The massive radiator surface is fine for passive cooling until about 300W. I can tell the cpu is doing more than usual, because I can hear the water pump (normally I can't hear it - yes I need to add rubber feet, then it'll be silent even when ramping up) in addition to all the hardware monitoring I do. Also leds are extremely important for troubleshooting. Anyone who built an am5 PC knows the pain of "memory training". Having leds on the MB to tell you what is going on is very useful. As for the typical "developer laptop" in my current place of work (and 3 previous ones - all fortune 300 companies) developers use either Windows or Linux laptops. Only managers use macs. How is this relevant? Well, because all these laptops have fans and you can tell when they're busy.
Doesn’t like itHasn’t owned it
Geekbench Ryzen 9 7950x is 2930 max, so if we're generous and give the 9950x 15% uplift we'll be at 3380, which is still 400 points or so behind apple silicon for a much higher clock speed and a multiplier larger power draw. Also the max memory bandwidth at 70GB/s or so is basically pathetic, trounced by ASi.
Likes itHasn’t owned it
The performance per dollar of Ryzen 7950X is many times higher than of any Epyc or Threadripper CPUs, even after adding the costs of the motherboards, coolers, cases and PSUs. The DRAM bandwidth per core is identical for Ryzen 7950X and for 96-core Genoa Epyc CPUs. On the other hand, the Epyc CPUs with high-core count have a better performance per watt. So the initial cost for a cluster of Ryzen servers is many times less. Depending on the cost of electricity, if an Epyc server is used 24/7, after some years the expenses with it may become lower than with Ryzen. If the server is used intermittently, the total cost of ownership may remain lower with Ryzen until the end of life. The only certain advantages of Epyc are the ability of aggregating a higher amount of memory, especially if it is preferable to have it inside a single box, and the faster inter-core communication for applications that use all cores (as opposed to the case when the cores are partitioned between weakly-coupled applications, e.g. between different virtual machines). The prices of the Epyc CPUs have increased a lot since their first generation until now. With Zen 1, a server with any Ryzen would not have been competitive with a server with Epyc. Meanwhile, the ratio between the prices per core of Epyc and Ryzen has increased a lot, while the ratio between the performance per core of Epyc and Ryzen has decreased a lot, because the clock frequency of Ryzens has become much greater while that of Epycs has inc…