readygpu

NVIDIA GeForce RTX 3090 vs NVIDIA GeForce RTX 5080

For running models locally, priced in Germany. At 128k context the first runs 9 models fully in memory, the second 5.

In short

The NVIDIA GeForce RTX 3090 has more memory for models: 24 GB against 16 GB. At 128k context the NVIDIA GeForce RTX 3090 runs 9 of the models we track fully in memory and the NVIDIA GeForce RTX 5080 5; only the NVIDIA GeForce RTX 3090 holds Gemma 4 26B-A4B. On the models both run fully in memory, the NVIDIA GeForce RTX 3090 and the NVIDIA GeForce RTX 5080 are about as fast as each other (estimated). In Germany the NVIDIA GeForce RTX 3090 costs 1.850 € at eBay and the NVIDIA GeForce RTX 5080 1.500 € at eBay: the NVIDIA GeForce RTX 5080 is 350 € cheaper.

Updated . Speeds are estimates; how they are worked out.

NVIDIA GeForce RTX 3090

1.850 €

eBay

Add to build
NVIDIA GeForce RTX 5080

1.500 €

eBay

Add to build

Specifications

SpecNVIDIA GeForce RTX 3090NVIDIA GeForce RTX 5080
GPUGeForce RTX 3090GeForce RTX 5080
Memory24 GB GDDR6X16 GB GDDR7
Memory bus384-bit256-bit
Memory bandwidth936 GB/s960 GB/s
FP16 compute71 TFLOPS113 TFLOPS
SoftwareCUDACUDA
Board power350 W360 W
PCIe generationGen 4Gen 5
PCIe lanesx16x16

What each runs

Estimated decode speed with the most precise quant that fits each one est.

ModelNVIDIA GeForce RTX 3090NVIDIA GeForce RTX 5080
Gemma 4 26B-A4B63tok/sUD-Q4_K_Moffload
gpt-oss 20B62tok/sMXFP4offload
Gemma 4 12B38tok/sQ8_049tok/sQ6_K
Qwen 3.5 9B42tok/sQ8_043tok/sQ8_0
Qwen 3.5 4B66tok/sQ8_067tok/sQ8_0
Ministral 3 8B25tok/sQ4_K_Moffload
Gemma 4 E4B48tok/sQ8_050tok/sQ8_0
LFM2.5 8B-A1B46tok/sQ8_049tok/sUD-Q6_K
Llama 3.1 8B25tok/sQ5_K_Moffload
Qwen 3.8 27Boffloadoffload
Qwen 3.5 122B-A10Boffloadwon't run
Qwen 3.6 27Boffloadoffload
Gemma 4 31Boffloadoffload
Mistral Small 4 119Boffloadwon't run
Qwen 3.6 35B-A3Boffloadoffload
Qwen 3.5 27Boffloadoffload
Qwen 3.5 35B-A3Boffloadoffload
GLM 4.7 Flashoffloadoffload
Devstral Small 2 24Boffloadoffload
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 Coder 30B-A3Boffloadoffload
Gemma 3 27Boffloadoffload
Mistral Small 3.2 24Boffloadoffload
Ministral 3 14Boffloadoffload
Qwen3 14Boffloadoffload
DeepSeek R1 0528 Qwen3 8Boffloadoffload
Qwen3 8Boffloadoffload
Phi-4 14Boffloadoffload
Granite 4.2 8Boffloadoffload
DeepSeek V4 Flashwon't runwon't run
GLM 5.3 Flashwon't runwon't run
Qwen 3.8 Flash Nextwon't runwon't run
MiniMax M2.7won't runwon't run
Nemotron 3 Super 120B-A12Bwon't runwon't run
Qwen3 Coder Nextwon't runwon't run
gpt-oss 120Bwon't runwon't run
GLM 4.5 Airwon't runwon't run
Qwen3 Next 80B-A3Bwon't runwon't run
Qwen3 32Bwon't runwon't run
DeepSeek R1 Distill Qwen 32Bwon't runwon't run
Llama 3.3 70Bwon't runwon't run

Questions

Which is better for local AI, the NVIDIA GeForce RTX 3090 or the NVIDIA GeForce RTX 5080?
Choose the NVIDIA GeForce RTX 3090 to run bigger models. Choose the NVIDIA GeForce RTX 5080 to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 3090 or the NVIDIA GeForce RTX 5080?
At 128k context the NVIDIA GeForce RTX 3090 runs 9 of the models we track fully in memory and the NVIDIA GeForce RTX 5080 5; only the NVIDIA GeForce RTX 3090 holds Gemma 4 26B-A4B.
Which is faster for local AI, the NVIDIA GeForce RTX 3090 or the NVIDIA GeForce RTX 5080?
On the models both run fully in memory, the NVIDIA GeForce RTX 3090 and the NVIDIA GeForce RTX 5080 are about as fast as each other (estimated).
What is the price difference between the NVIDIA GeForce RTX 3090 and the NVIDIA GeForce RTX 5080?
In Germany the NVIDIA GeForce RTX 3090 costs 1.850 € at eBay and the NVIDIA GeForce RTX 5080 1.500 € at eBay: the NVIDIA GeForce RTX 5080 is 350 € cheaper.

More comparisons