Skip to content

Rig score · nvidia

Device readout 2026-08-03
Rig Score A tier
75%
Nvidia GeForce RTX 3090 (24GB) · 24 GB
runs 101 of 135 models · biggest Seed-OSS 36B Instruct
localmodel.run/rig

Nvidia GeForce RTX 3090 (24GB)

Runs 101 of 135 models (75%)

Excellent, runs up to ~32B comfortably.

Biggest it can run: Seed-OSS 36B Instruct

Grade
A
Runnable
101
Total
135
Coverage
75%

What Nvidia GeForce RTX 3090 (24GB) can run

At 24 GB of VRAM, Nvidia GeForce RTX 3090 (24GB) runs 101 of 135 tracked local models, 75% coverage that earns a A. The largest it handles is Seed-OSS 36B Instruct at 36B parameters; anything bigger needs more memory or a lower quantization.

Only the 24 GB of VRAM drives speed: a model that spills into system RAM slows sharply. Keep the weights plus KV cache under VRAM and prefer Q4_K_M to leave headroom.

88 run well 13 tight fit 34 too big

Top models on Nvidia GeForce RTX 3090 (24GB)

FAQ

What local AI rig score does Nvidia GeForce RTX 3090 (24GB) get?

Nvidia GeForce RTX 3090 (24GB) scores A: it runs 101 of 135 tracked local LLMs (75%). The biggest it can run is Seed-OSS 36B Instruct.

How big a model can Nvidia GeForce RTX 3090 (24GB) run?

Nvidia GeForce RTX 3090 (24GB) runs models up to Seed-OSS 36B Instruct (36B parameters) at Q4_K_M. Speed depends on keeping the whole model inside VRAM.

Is Nvidia GeForce RTX 3090 (24GB) good for running local LLMs?

Only the 24 GB of VRAM drives speed: a model that spills into system RAM slows sharply. Keep the weights plus KV cache under VRAM and prefer Q4_K_M to leave headroom.

Want your own? Check your rig on the homepage →

Score from coverage of 135 tracked models, estimated with our memory methodology.