Sunk Cost sunkcost.ai Data checked 2026-09-03

NVIDIA GeForce RTX 4090, 24GB vs NVIDIA GeForce RTX 3090, 24GB for local AI

Both hold 24 of the 39 open models here. The GeForce RTX 3090, 24GB costs $100 less, both priced as the card alone, without the PC around either. On Qwen3.8 27B, the strongest model both hold, the GeForce RTX 4090, 24GB is about 1.2× faster: 44 tok/s against 38, both estimated from memory bandwidth. The GeForce RTX 3090, 24GB pays for itself sooner, in 19 years against 21 years at 500k tokens a day. Both are previous-generation parts, so every figure here is priced at what they launched at rather than at prices you can pay today.

NVIDIA GeForce RTX 4090, 24GBNVIDIA GeForce RTX 3090, 24GB
Price$1,599card only$1,499card only
Memory24 GB24 GB
Usable by the GPU23 GB23 GB
Memory bandwidth1008 GB/s936 GB/s
Power under load450 W350 W
Models that fit2424
Best model it runsQwen3.8 27BQwen3.8 27B
Speed on that model44 tok/s estimated38 tok/s estimated
Pay-back on that modelPays back in 21 yearsPays back in 19 years

Run the numbers on the NVIDIA GeForce RTX 4090, 24GB · or the NVIDIA GeForce RTX 3090, 24GB

How much use it takes to pay back

Everything above is at 500k tokens a day. Pay-back moves with how much you actually run, so here are both machines on Qwen3.8 27B, the strongest model both hold, at the five levels of use the calculator names. The NVIDIA GeForce RTX 3090, 24GB pays back sooner at every level of use, so this is not a choice that turns on how hard you work it.

A day's useNVIDIA GeForce RTX 4090, 24GBNVIDIA GeForce RTX 3090, 24GB
50ka few chats a day206 years191 years
200klight assistant use51 years48 years
1Ma moderate coding-assistant day10 years9.6 years
4Mheavy coding with an agent2.6 years2.4 years
20Magents running most of the day6.2 months5.7 months

Run the NVIDIA GeForce RTX 4090, 24GB at 20M tokens a day · or the NVIDIA GeForce RTX 3090, 24GB

Memory is not what separates them

Every model on this list that fits one machine fits the other, and not only at 32k of context: across all 39 models the calculator counts, at every context from 4k to 256k, there is no model one holds and the other does not. Both leave 23 GB to the GPU. So the choice between them is speed, price and power, not what they can hold.

The assumptions behind both columns

Both columns use the same usage: 500k tokens a day at 15:1 input to output, 32k of context, $0.17 per kWh, and today's API prices held flat. Speeds marked estimated are worked out from memory bandwidth rather than measured, and pay-back scales with them. Graphics cards are priced as the card alone, so add the PC around one before comparing it with a complete computer. Change any of it in the calculator.

More head to head: everything the NVIDIA GeForce RTX 4090, 24GB runs · everything the NVIDIA GeForce RTX 3090, 24GB runs · every other match-up · the quickest pay-back at each level of use · every model against the frontier