NVIDIA GeForce RTX 5090

“My favorite, to be honest, is a 5090 with a Qwen 27B because that one is good for quick hitters and flies”

“Personally I think the price is way too high right now. It’s a power hungry gaming GPU.”

“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”

“The 8x 5090s will require a dedicated datacentre grade power source.”

“it's like the worst ADHD team member and requires constant supervision and review from larger models”

“It can bench comparable to the RTX 6000 Pro cards and is near guaranteed to outperform M5 Ultra.”

“doesn't outperform my RTX 5090 with inference by anything significant on the good local models”

“they will become obsolete much slower if at all compared to when the mac will be barely usable”

“Even going with two 5090s, you now have to shard your model and that is a PITA.”

“Using a RTX 5090 ($3~4k), I can run Qwen 3.8 27B at ~180 TPS with ninfer”

“Really happy I got a new PC last year with 128 GB of RAM, 4 TB SSD, and an RTX 5090.”

“with a 3080 Ti and now a 5090 I have no issue playing almost all the games on steam”

“if you want the best possible AI machine at below $5k... actually you should probably just buy an RTX 3090 or 5090”

“my 5090 with 32GB VRAM is usually somewhere between 60 to 100 tok/s with mtp”

“even on a 5090 you can get a reasonable amount of inference for way less than paying for Opus”

“24 GB in RTX 4090 or RTX 5090 (MSRP $1999 but in practice $3000-$4000 at the moment)”

“or a single 5090 ($2k, but only 32GB, the worst option of the three)”

“I can fit models into the 32GB of vram but my context window ends up being tiny”

“Yes, I'd recommend a 5090 over the DGX Spark if your goal is general automation.”

“I would probably buy a more AI dedicated machine but I also don't regret finally being able to play Cyberpunk in 4k”

“It still feels extremely fast, even though it's about 8 year old technology with a newer video card”

“The 5090 is crap for inference. Unless you like dummy models, sure they will run at light speed.”

“With only 32gb of vram, you can only run small/quantized models, in which case what's the point?”

“If you graph the tokens per second on the 5090, your jaw will hit the floor at how cheap it is”

“RTX 5090 gives me 50-60 tok/sec and 260k context with Unsloth's 5-bit quantization”

“The RTX 5090 has an incredible amount of compute performance for matrix operations and a lot of memory bandwidth.”

“cards like RTX 5090 which have very high performance for the price but rather little memory”

“renting an RTX 5090 for an evening of image generation for a dollar or two is way more fun”

“the 5090 realistically never was and usually goes for 50-100% above MSRP”

“running 2 to 4 5090 will beat anything Apple has to offer for both inference and training”

“My 5090 is unbelievably fast at inference even if it can't load gigantic models”

“I got an Olares One system with a 24GB (consumer not 32GB) NVIDIA RTX 5090 for less than $3k at the Kickstarter price”

“For fast inference, you’d be hard pressed to beat an Nvidia RTX 5090 GPU.”

“over a 5090 to an RTX 6000 Pro in my machine and be confident that my CUDA code will scale”

“it's a bit underwhelming, and for $3000 if I didn't also use it for gaming I'd have been pretty disappointed”

“Bought a slightly overpriced, even by its own standards, 5090 in May”

“I have a RTX 5090 + 96GB DDR5-6000 that crushes the spark on prompt processing”

“Given the power requirements involved that's actually a regression.”

“A 5090 needs about a minute to generate an image with a basic workflow with Flux.2-dev”

“A 3x5090 rig will require significant tuning/downclocking to be run from a single North American 15A plug”