The stuff Hacker News actually recommends.

GPUs and CPUs

AMD Ryzen 7 vs NVIDIA GeForce RTX

Hacker News owners slightly favor the NVIDIA GeForce RTX.

AMD Ryzen 7NVIDIA GeForce RTX
Owners with an opinion74617
Positive verdicts83% of 4776% of 416
Positive/negative since 202422/7214/71
Happy after 3+ years210
Longest happy owner3 yrs6 yrs
Praised forperformance and valueperformance and value
Criticized forreliability and noisenoise
Newest comment

Updated

What owners wrote about both

AMD Ryzen 7: NeutralNVIDIA GeForce RTX: Likes it
I downloaded Ollama ( https://github.com/ollama/ollama/releases ) and experimented with a few Qwen models ( https://huggingface.co/Qwen/collections ). My performance when using an RTX 5070 12GiB VRAM, Ryzen 7 9700X 8 cores CPU, 32GiB DDR5 6000MT (2 sticks): - "qwen2.5:7b": ~128 tokens/second (this model fits 100% in the VRAM). - "qwen2.5:32b": ~4.6 tokens/second. - "qwen3:30b-a3b": ~42 tokens/second (this is a MoE model with multiple specialized "brains") (this uses all 12GiB VRAM + 9GiB system RAM, but the GPU usage during tests is only ~25%). - qwen3.5:35b-a3b: ~17 tokens/second, but it's highly unstable and crashes -> currently not usable for me. So currently my sweet spot is "qwen3:30b-a3b" - even if the model doesn't completely fit on the GPU it's still fast enough. "qwen3.5" was disappointing so far, but maybe things will change in the future (maybe Ollama needs some special optimizations for the 3.5-series?). I would therefore deduce that the most important thing is the amount of VRAM and that performance would be similar even when using an older GPU (e.g. an RTX 3060 with as well 12GiB RAM)? Performance without a GPU, tested by using a Ryzen 9 5950X 16 cores CPU, 128GiB DDR4 3200 MT: - "qwen2.5:7b": ~9 tokens/second - "qwen3:32b": ~2 tokens/second - "qwen3:30b-a3b": ~16 tokens/second
AMD Ryzen 7: NeutralNVIDIA GeForce RTX: Doesn’t like it
To add another datapoint, I've been running the 131GB (140GB on disk) 1.58 bit dynamic quant from Unsloth with 4k context on my 32GB Ryzen 7 2700X (8 cores, 3.70 GHz), and achieved exactly the same speed - around 0.15 tps on average, sometimes dropping to 0.11, tps occasionally going up to 0.16 tps. Roughly 1/2 of your specs, roughly 1/2 smaller quant, same tps. I've had to disable the overload safeties in LM Studio and tweak with some loader parameters to get the model to run mostly from disk (NVMe SSD), but once it did, it also used very little CPU! I tried offloading to GPU, but my RTX 4070 Ti (12GB VRAM) can take at most 4 layers, and it turned out to make no difference in tps. My RAM is DDR4, maybe switching to DDR5 would improve things? Testing that would require replacing everything but the GPU, though, as my motherboard is too old :/.
AMD Ryzen 7: NeutralNVIDIA GeForce RTX: Likes it
Other than feeding sensitive documents? I’m not sure. OpenAI has certainly gone out of its way to eliminate the need for local LLMs- they offer fine-tuning of GPT 3.5 and 4, so it’s harder to argue you might get better results from a local model for a particular task with particular data. Though I don’t have personal experience with the ChatGPT fine-tuning. It’s fun running models from HuggingFace on my computer. Finally, something that utilizes my computer’s 64GB of RAM and 24GB of VRAM. It’s neat seeing the immense performance difference between CPU (Ryzen 7 5700X) and GPU (RTX 3090) offloading. I think as with most “Cloud vs on-prem” arguments, it comes down to cost vs convenience. Building an application on Azure or AWS is as easy as it gets, but if money is scarce, you can’t beat on-prem for raw resources. I’m writing a program right now that will query ChatGPT 4 with… A LOT of tokens. We project it will cost between $5k and $15k and probably run for around 2 days. *OR* I could feed that same data through a local model running on the RTX 3090 and it’ll cost like $20 in electricity, and take maybe 6 days.
AMD Ryzen 7: NeutralNVIDIA GeForce RTX: Likes it
I’m running Alan Wake 2 on an RTX 3080 with a 7800X3D and the first few sections in the forest (don’t think describing forest scenes in Alan Wake 2 is a spoiler here) ran around 30fps, and then the absolutely sumptuous next few levels (man the maps are gorgeous) have been running at 60fps rendered at 1080p upscaled to 1440p. It didn’t seem like turning down settings caused a huge increase in frame rate so I just put everything to max and man it looks great. So you at least feel like there’s a reason your graphics card is running at 82°C and your fans are spinning up. On the other hand, my wife was a huge Cities Skylines 1 player and bounced off the game pretty hard, as the low frame rates doesn’t come with any sort of real upside.
AMD Ryzen 7: Likes itNVIDIA GeForce RTX: Likes it
I only run models I can run locally. Perhaps I'm framing my question incorrectly. AI is being used in contexts that involve life and death. Being right more often is not good enough in that context. If we are going to put AI in drones and have them autonomously acquire and fire on enemies, perhaps the fact that all AI hallucinates at all makes it morally and ethically unusable for purposes in which the stakes are very high, such as life and death. This is what scares me about it. And also what I was able to accomplish air-gapped with a Ryzen 7 and RTX 3060 12GB scared me. This is not the kind of thing we should all have to speculate about, someone should have solid answers. Perhaps the fact that some, and maybe most, AI models are black boxes even to those that trained them, should have been the first red flag and that was years ago.
AMD Ryzen 7: NeutralNVIDIA GeForce RTX: Neutral
I've been on the same PSU for I think 13 years now, its currently running my Ryzen 7 3700x and RTX4070 desktop. I suppose if its not a great quality PSU or its already suspected of causing issues then replacing is a good idea.
AMD Ryzen 7: Likes itNVIDIA GeForce RTX: Likes it
Cheers, I've been wanting to get into doing something else with my 4090 order than multi monitor simulator gaming, quad screen workstation work - and this will get me kicked off! The 4090 is an absolute beast, runs extremely quiet and simply powers through everything. DCS pushes it to the limit, but the resulting experience is simply stunning. Mine's coupled to a 7800x3d which uses hardly any power at all, absolutely love it.
AMD Ryzen 7: NeutralNVIDIA GeForce RTX: Neutral
I'm a recent (mostly) convert. So far Anno 1800 has an issue where multiplayer games only connect if I play on Windows (but single player runs flawlessly in Linux Mint.) Every other game I've played has been great. StarCraft II (in Bottles), Conan, Valheim, Northgard (so far.) PC gaming on Linux is not perfect, but it's really damn good. (This is on a Ryzen 7 + Geforce RTX laptop)
AMD Ryzen 7: Likes itNVIDIA GeForce RTX: Likes it
A 16A circuit allows for 3.8kW or something like that @ 240v. With these ludicrous power requirements, you may in fact need to rethink how you use your power. E.g. if on same as a non-heat pump drier, you'd have to make a choice between gaming and drying clothes. Having said that I saw a reference to a 4090 offering 95% of the perf at 60% of the power usage if undervolted, so that becomes an attractive option now. I absolutely love my 5800X3D's insanely low power usage (insane = performance per watt for gaming in simulator titles where it runs circles around Intel).