readygpu

NVIDIA GeForce RTX 3090 vs NVIDIA GeForce RTX 4080 Super

For running models locally, priced in the US. At 64k context the first runs 22 models fully in memory, the second 10.

In short

The NVIDIA GeForce RTX 3090 has more memory for models: 24 GB against 16 GB. At 64k context the NVIDIA GeForce RTX 3090 runs 22 of the models we track fully in memory and the NVIDIA GeForce RTX 4080 Super 10; only the NVIDIA GeForce RTX 3090 holds Qwen 3.8 27B. On the models both run fully in memory, the NVIDIA GeForce RTX 3090 is about 1.3× as fast as the NVIDIA GeForce RTX 4080 Super (estimated, median across models). In the US the NVIDIA GeForce RTX 3090 costs $1,600 at eBay and the NVIDIA GeForce RTX 4080 Super $1,199 at Amazon: the NVIDIA GeForce RTX 4080 Super is $401 cheaper.

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

NVIDIA GeForce RTX 3090

$1,600

eBay

Add to build
NVIDIA GeForce RTX 4080 Super

$1,199

Amazon

Add to build

Specifications

SpecNVIDIA GeForce RTX 3090NVIDIA GeForce RTX 4080 Super
GPUGeForce RTX 3090GeForce RTX 4080 Super
Memory24 GB GDDR6X16 GB GDDR6X
Memory bus384-bit256-bit
Memory bandwidth936 GB/s736 GB/s
FP16 compute71 TFLOPS104 TFLOPS
SoftwareCUDACUDA
Board power350 W320 W
PCIe generationGen 4Gen 4
PCIe lanesx16x16

What each runs

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

ModelNVIDIA GeForce RTX 3090NVIDIA GeForce RTX 4080 Super
Qwen 3.8 27B28tok/sUD-Q4_K_Moffload
Qwen 3.6 27B24tok/sQ5_K_Moffload
Qwen 3.6 35B-A3B107tok/sUD-Q4_K_Moffload
Qwen 3.5 27B27tok/sQ4_K_Moffload
Gemma 4 26B-A4B72tok/sUD-Q5_K_Moffload
Qwen 3.5 35B-A3B107tok/sQ4_K_Moffload
GLM 4.7 Flash53tok/sQ4_K_Moffload
gpt-oss 20B86tok/sMXFP468tok/sMXFP4
Gemma 4 12B41tok/sQ8_032tok/sQ8_0
Qwen 3.5 9B50tok/sQ8_039tok/sQ8_0
Gemma 3 27B26tok/sQ4_K_Moffload
Ministral 3 14B27tok/sQ6_Koffload
Qwen3 14B25tok/sQ6_Koffload
DeepSeek R1 0528 Qwen3 8B32tok/sQ8_031tok/sQ4_K_M
Qwen3 8B32tok/sQ8_031tok/sQ4_K_M
Phi-4 14B24tok/sQ5_K_Moffload
Qwen 3.5 4B87tok/sQ8_068tok/sQ8_0
Ministral 3 8B32tok/sQ8_030tok/sQ5_K_M
Granite 4.2 8B29tok/sQ8_0offload
Gemma 4 E4B57tok/sQ8_045tok/sQ8_0
LFM2.5 8B-A1B81tok/sQ8_064tok/sQ8_0
Llama 3.1 8B38tok/sQ6_K30tok/sQ6_K
Qwen 3.5 122B-A10Boffloadwon't run
Gemma 4 31Boffloadoffload
Qwen3 Coder Nextoffloadwon't run
Mistral Small 4 119Boffloadoffload
Qwen3 Next 80B-A3Boffloadwon't run
Devstral Small 2 24Boffloadoffload
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 Coder 30B-A3Boffloadoffload
Qwen3 32Boffloadoffload
Mistral Small 3.2 24Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
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
gpt-oss 120Bwon't runwon't run
GLM 4.5 Airwon'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 4080 Super?
Choose the NVIDIA GeForce RTX 3090 to run bigger models. Choose the NVIDIA GeForce RTX 3090 for speed. Choose the NVIDIA GeForce RTX 4080 Super to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 3090 or the NVIDIA GeForce RTX 4080 Super?
At 64k context the NVIDIA GeForce RTX 3090 runs 22 of the models we track fully in memory and the NVIDIA GeForce RTX 4080 Super 10; only the NVIDIA GeForce RTX 3090 holds Qwen 3.8 27B.
Which is faster for local AI, the NVIDIA GeForce RTX 3090 or the NVIDIA GeForce RTX 4080 Super?
On the models both run fully in memory, the NVIDIA GeForce RTX 3090 is about 1.3× as fast as the NVIDIA GeForce RTX 4080 Super (estimated, median across models).
What is the price difference between the NVIDIA GeForce RTX 3090 and the NVIDIA GeForce RTX 4080 Super?
In the US the NVIDIA GeForce RTX 3090 costs $1,600 at eBay and the NVIDIA GeForce RTX 4080 Super $1,199 at Amazon: the NVIDIA GeForce RTX 4080 Super is $401 cheaper.

More comparisons