# NVIDIA GeForce RTX 5090

102 Hacker News commenters recommended NVIDIA GeForce RTX 5090 and 37 criticized it, November 2025 to November 2026. It was recommended in 12 of 13 months; owners who said how long report a median of 1 years (3 owners). It meets the Hacker Approved badge rule.

**Verdict:** A top consumer GPU for very fast local AI inference and 4K gaming, but 32GB VRAM limits larger models and street prices run well above MSRP.

## Why people recommend it

- Very fast local AI inference (9 comments): "The RTX 5090 has an incredible amount of compute performance for matrix operations and a lot of memory bandwidth." ([source](https://news.ycombinator.com/item?id=48138610)) "My favorite, to be honest, is a 5090 with a Qwen 27B because that one is good for quick hitters and flies" ([source](https://news.ycombinator.com/item?id=49834451)) "If you graph the tokens per second on the 5090, your jaw will hit the floor at how cheap it is" ([source](https://news.ycombinator.com/item?id=48259561))
- Beats Macs and DGX Spark (5 comments): "It can bench comparable to the RTX 6000 Pro cards and is near guaranteed to outperform M5 Ultra." ([source](https://news.ycombinator.com/item?id=49652563)) "doesn't outperform my RTX 5090 with inference by anything significant on the good local models" ([source](https://news.ycombinator.com/item?id=49513949)) "running 2 to 4 5090 will beat anything Apple has to offer for both inference and training" ([source](https://news.ycombinator.com/item?id=47540101))
- Great for high-end gaming (3 comments): "I would probably buy a more AI dedicated machine but I also don't regret finally being able to play Cyberpunk in 4k" ([source](https://news.ycombinator.com/item?id=48539874)) "Really happy I got a new PC last year with 128 GB of RAM, 4 TB SSD, and an RTX 5090." ([source](https://news.ycombinator.com/item?id=49352564)) "with a 3080 Ti and now a 5090 I have no issue playing almost all the games on steam" ([source](https://news.ycombinator.com/item?id=49099323))
- Strong performance for the price (3 comments): "If you graph the tokens per second on the 5090, your jaw will hit the floor at how cheap it is" ([source](https://news.ycombinator.com/item?id=48259561)) "even on a 5090 you can get a reasonable amount of inference for way less than paying for Opus" ([source](https://news.ycombinator.com/item?id=48645617)) "cards like RTX 5090 which have very high performance for the price but rather little memory" ([source](https://news.ycombinator.com/item?id=47941934))

## What people warn about

- 32GB VRAM limits bigger models (6 comments): "cards like RTX 5090 which have very high performance for the price but rather little memory" ([source](https://news.ycombinator.com/item?id=47941934)) "the moment you want to run the more capable models that will no longer fit in a single 5090's memory, performance falls off a cliff" ([source](https://news.ycombinator.com/item?id=49792414)) "With only 32gb of vram, you can only run small/quantized models, in which case what's the point?" ([source](https://news.ycombinator.com/item?id=48259765))
- Sells well above MSRP (4 comments): "24 GB in RTX 4090 or RTX 5090 (MSRP $1999 but in practice $3000-$4000 at the moment)" ([source](https://news.ycombinator.com/item?id=48625979)) "Personally I think the price is way too high right now. It’s a power hungry gaming GPU." ([source](https://news.ycombinator.com/item?id=49792987)) "the 5090 realistically never was and usually goes for 50-100% above MSRP" ([source](https://news.ycombinator.com/item?id=47681130))
- High power draw (4 comments): "A 3x5090 rig will require significant tuning/downclocking to be run from a single North American 15A plug" ([source](https://news.ycombinator.com/item?id=46112074)) "Personally I think the price is way too high right now. It’s a power hungry gaming GPU." ([source](https://news.ycombinator.com/item?id=49792987)) "The 8x 5090s will require a dedicated datacentre grade power source." ([source](https://news.ycombinator.com/item?id=49792243))
- Multi-GPU setups are painful (3 comments): "A 3x5090 rig will require significant tuning/downclocking to be run from a single North American 15A plug" ([source](https://news.ycombinator.com/item?id=46112074)) "Even going with two 5090s, you now have to shard your model and that is a PITA." ([source](https://news.ycombinator.com/item?id=49442782)) "The 8x 5090s will require a dedicated datacentre grade power source." ([source](https://news.ycombinator.com/item?id=49792243))

## Alternatives hackers recommend

- [NVIDIA GeForce RTX 3090](https://hackerapproved.com/p/nvidia-geforce-rtx-3090.md): 116 recommend
- [NVIDIA RTX PRO 6000](https://hackerapproved.com/p/nvidia-rtx-pro-6000.md): 77 recommend
- [Nvidia GPUs](https://hackerapproved.com/p/nvidia-gpus.md): 67 recommend
- [AMD Radeon GPU](https://hackerapproved.com/p/amd-gpus.md): 48 recommend
- [AMD Radeon AI Pro R9700](https://hackerapproved.com/p/amd-radeon-ai-pro-r9700.md): 45 recommend

## Where to get it

- [See price on Amazon](https://www.amazon.com/s?k=NVIDIA+GeForce+RTX+5090+graphics+card&tag=hackerapprove-20) (affiliate link)
- [Official site](https://www.nvidia.com/en-us/geforce/graphics-cards/50-series/rtx-5090/)

## Cite as

Hacker Approved, "NVIDIA GeForce RTX 5090", https://hackerapproved.com/p/nvidia-geforce-rtx-5090/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).