readygpu

NVIDIA GeForce RTX 3080 10GB vs NVIDIA GeForce RTX 4080 Super

For running models locally, priced in Canada. At 8k context the first runs 10 models fully in memory, the second 16.

In short

The NVIDIA GeForce RTX 4080 Super has more memory for models: 16 GB against 10 GB. At 8k context the NVIDIA GeForce RTX 4080 Super runs 16 of the models we track fully in memory and the NVIDIA GeForce RTX 3080 10GB 10; only the NVIDIA GeForce RTX 4080 Super holds Devstral Small 2 24B. On the models both run fully in memory, the NVIDIA GeForce RTX 3080 10GB is about 1.3× as fast as the NVIDIA GeForce RTX 4080 Super (estimated, median across models). In Canada the NVIDIA GeForce RTX 3080 10GB costs $769 at Amazon and the NVIDIA GeForce RTX 4080 Super $2,000 at Amazon: the NVIDIA GeForce RTX 3080 10GB is $1,231 cheaper.

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

NVIDIA GeForce RTX 3080 10GB

$769

Amazon

Add to build
NVIDIA GeForce RTX 4080 Super

$2,000

Amazon

Add to build

Specifications

SpecNVIDIA GeForce RTX 3080 10GBNVIDIA GeForce RTX 4080 Super
GPUGeForce RTX 3080 10GBGeForce RTX 4080 Super
Memory10 GB GDDR6X16 GB GDDR6X
Memory bus320-bit256-bit
Memory bandwidth760 GB/s736 GB/s
FP16 compute59.5 TFLOPS104 TFLOPS
SoftwareCUDACUDA
Board power320 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 3080 10GBNVIDIA GeForce RTX 4080 Super
Devstral Small 2 24Boffload29tok/sQ4_K_M
gpt-oss 20Boffload104tok/sMXFP4
Gemma 4 12B53tok/sQ5_K_M35tok/sQ8_0
Qwen 3.5 9B61tok/sQ6_K46tok/sQ8_0
Mistral Small 3.2 24Boffload29tok/sQ4_K_M
Ministral 3 14Boffload29tok/sQ8_0
Qwen3 14Boffload34tok/sQ6_K
DeepSeek R1 0528 Qwen3 8B59tok/sQ6_K46tok/sQ8_0
Qwen3 8B59tok/sQ6_K46tok/sQ8_0
Phi-4 14Boffload33tok/sQ6_K
Qwen 3.5 4B98tok/sQ8_095tok/sQ8_0
Ministral 3 8B58tok/sQ6_K45tok/sQ8_0
Granite 4.2 8B53tok/sQ6_K43tok/sQ8_0
Gemma 4 E4B56tok/sQ8_054tok/sQ8_0
LFM2.5 8B-A1B228tok/sUD-Q6_K187tok/sQ8_0
Llama 3.1 8B61tok/sQ6_K60tok/sQ6_K
Qwen 3.8 27Boffloadoffload
Qwen 3.5 122B-A10Bwon't runoffload
Qwen 3.6 27Boffloadoffload
Gemma 4 31Boffloadoffload
Mistral Small 4 119Bwon't runoffload
Qwen 3.6 35B-A3Boffloadoffload
Qwen 3.5 27Boffloadoffload
Gemma 4 26B-A4Boffloadoffload
Qwen 3.5 35B-A3Boffloadoffload
GLM 4.7 Flashoffloadoffload
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 Coder 30B-A3Boffloadoffload
Qwen3 32Boffloadoffload
Gemma 3 27Boffloadoffload
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
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
Llama 3.3 70Bwon't runwon't run

Questions

Which is better for local AI, the NVIDIA GeForce RTX 3080 10GB or the NVIDIA GeForce RTX 4080 Super?
Choose the NVIDIA GeForce RTX 4080 Super to run bigger models. Choose the NVIDIA GeForce RTX 3080 10GB for speed. Choose the NVIDIA GeForce RTX 3080 10GB to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 3080 10GB or the NVIDIA GeForce RTX 4080 Super?
At 8k context the NVIDIA GeForce RTX 4080 Super runs 16 of the models we track fully in memory and the NVIDIA GeForce RTX 3080 10GB 10; only the NVIDIA GeForce RTX 4080 Super holds Devstral Small 2 24B.
Which is faster for local AI, the NVIDIA GeForce RTX 3080 10GB or the NVIDIA GeForce RTX 4080 Super?
On the models both run fully in memory, the NVIDIA GeForce RTX 3080 10GB 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 3080 10GB and the NVIDIA GeForce RTX 4080 Super?
In Canada the NVIDIA GeForce RTX 3080 10GB costs $769 at Amazon and the NVIDIA GeForce RTX 4080 Super $2,000 at Amazon: the NVIDIA GeForce RTX 3080 10GB is $1,231 cheaper.

More comparisons