readygpu

NVIDIA GeForce RTX 4080 Super vs NVIDIA GeForce RTX 5060 Ti 16GB

For running models locally, priced in Canada. At 8k context the first runs 41 models fully in memory, the second 41.

In short

Both have 16 GB of memory for models; the NVIDIA GeForce RTX 4080 Super has 736 GB/s of bandwidth and the NVIDIA GeForce RTX 5060 Ti 16GB 448 GB/s. At 8k context both run the same 41 models we track fully in memory. On the models both run fully in memory, the NVIDIA GeForce RTX 4080 Super is about 1.6× as fast as the NVIDIA GeForce RTX 5060 Ti 16GB (estimated, median across models). In Canada the NVIDIA GeForce RTX 4080 Super costs $1,599 at eBay (used) and the NVIDIA GeForce RTX 5060 Ti 16GB $1,120 at Amazon: the NVIDIA GeForce RTX 5060 Ti 16GB is $479 cheaper.

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

NVIDIA GeForce RTX 4080 Super

$1,599

eBay, used (asking)

Add to build
NVIDIA GeForce RTX 5060 Ti 16GB

$1,120

Amazon

Add to build

Specifications

SpecNVIDIA GeForce RTX 4080 SuperNVIDIA GeForce RTX 5060 Ti 16GB
GPUGeForce RTX 4080 SuperGeForce RTX 5060 Ti 16GB
Memory16 GB GDDR6X16 GB GDDR7
Memory bus256-bit128-bit
Memory bandwidth736 GB/s448 GB/s
FP16 compute104 TFLOPS47 TFLOPS
SoftwareCUDACUDA
Board power320 W180 W
PCIe generationGen 4Gen 5
PCIe lanesx16x8

What each runs

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

ModelNVIDIA GeForce RTX 4080 SuperNVIDIA GeForce RTX 5060 Ti 16GB
Devstral Small 2 24B29tok/sQ4_K_M18tok/sQ4_K_M
gpt-oss 20B104tok/sMXFP463tok/sMXFP4
Gemma 4 12B35tok/sQ8_021tok/sQ8_0
Qwen 3.5 9B46tok/sQ8_028tok/sQ8_0
Mistral Small 3.2 24B29tok/sQ4_K_M18tok/sQ4_K_M
Qwen3 14B34tok/sQ6_K21tok/sQ6_K
Ministral 3 14B29tok/sQ8_018tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B46tok/sQ8_028tok/sQ8_0
Qwen3 8B46tok/sQ8_028tok/sQ8_0
Phi-4 14B33tok/sQ6_K20tok/sQ6_K
Qwen 3.5 4B95tok/sQ8_058tok/sQ8_0
Ministral 3 8B45tok/sQ8_027tok/sQ8_0
Granite 4.2 8B43tok/sQ8_026tok/sQ8_0
Gemma 4 E4B54tok/sQ8_033tok/sQ8_0
LFM2.5 8B-A1B187tok/sQ8_0114tok/sQ8_0
Llama 3.1 8B60tok/sQ6_K36tok/sQ6_K
Qwen2.5 0.5B722tok/sQ8_0440tok/sQ8_0
Qwen3.5 0.8B490tok/sQ8_0298tok/sQ8_0
Qwen3.5 2B294tok/sQ5_K_M179tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B214tok/sQ8_0130tok/sQ8_0
MiniCPM5 2B151tok/sQ8_092tok/sQ8_0
LFM2.5 2.6B135tok/sQ8_082tok/sQ8_0
LFM2.5 VL 3B135tok/sQ8_082tok/sQ8_0
Spark X2.5 4B134tok/smlx-4bit82tok/smlx-4bit
Kimi VL A3B Thinking 2506126tok/sQ4_K_M76tok/sQ4_K_M
granite vision 4.1 4b106tok/sQ8_065tok/sQ8_0
granite 4.2 3b100tok/sQ8_061tok/sQ8_0
Kimi VL A3B98tok/smlx-6bit60tok/smlx-6bit
Mellum2.1 12B A2.5B Thinking97tok/sQ8_059tok/sQ8_0
FrogNano 4B 260992tok/sQ8_056tok/sQ8_0
DeepSeek R1 Distill Qwen 7B53tok/sQ8_032tok/sQ8_0
GLM 4 9B 041453tok/smlx-5bit32tok/smlx-5bit
DeepSeek R1 Distill Llama 8B48tok/sQ8_029tok/sQ8_0
Ministral 3 8B Reasoning 251245tok/sQ8_027tok/sQ8_0
GLM 4.6V Flash44tok/sQ8_027tok/sQ8_0
GLM 4.1V 9B Thinking38tok/smlx-8bit23tok/smlx-8bit
DeepSeek R1 Distill Qwen 14B33tok/sQ6_K20tok/sQ6_K
Devstral Small 250729tok/sQ4_K_M18tok/sQ4_K_M
Magistral Small 250629tok/sQ4_K_M18tok/sQ4_K_M
Magistral Small 250729tok/sQ4_K_M18tok/sQ4_K_M
Magistral Small 250929tok/sQ4_K_M18tok/sQ4_K_M
Qwen 3.8 27Boffloadoffload
Qwen 3.5 122B-A10Boffloadoffload
Qwen 3.6 27Boffloadoffload
Gemma 4 31Boffloadoffload
Mistral Small 4 119Boffloadoffload
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
Qwen3 Coder 30B-A3Boffloadoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 32Boffloadoffload
Gemma 3 27Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
LFM2.5 24B A2Boffloadoffload
granite 4.2 30boffloadoffload
Qwen3.8 27B OBLITERATEDoffloadoffload
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
DeepSeek R1won't runwon't run
DeepSeek R1 0528won't runwon't run
DeepSeek R1 Distill Llama 70Bwon't runwon't run
DeepSeek R1 Zerowon't runwon't run
DeepSeek V3 0324won't runwon't run
DeepSeek V3.1won't runwon't run
DeepSeek V3.1 Terminuswon't runwon't run
DeepSeek V3.2won't runwon't run
DeepSeek V4 Flash 0731won't runwon't run
DeepSeek V4 Flash Vision Expwon't runwon't run
Devstral 2 123B Instruct 2512won't runwon't run
GLM 4.5won't runwon't run
GLM 4.5Vwon't runwon't run
GLM 4.6won't runwon't run
GLM 4.6Vwon't runwon't run
GLM 4.7won't runwon't run
GLM 5won't runwon't run
GLM 5.1won't runwon't run
GLM 5.2won't runwon't run
GLM 5.3won't runwon't run
Kimi Dev 72Bwon't runwon't run
Kimi K2won't runwon't run
Kimi K2 Instruct 0905won't runwon't run
Kimi K2 Thinkingwon't runwon't run
Kimi K2.5won't runwon't run
MiniMax M2won't runwon't run
MiniMax M2.1won't runwon't run
MiniMax M2.5won't runwon't run
MiniMax M3won't runwon't run
Mistral Medium 3.5 128Bwon't runwon't run

Questions

Which is better for local AI, the NVIDIA GeForce RTX 4080 Super or the NVIDIA GeForce RTX 5060 Ti 16GB?
Choose the NVIDIA GeForce RTX 4080 Super for speed. Choose the NVIDIA GeForce RTX 5060 Ti 16GB to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 4080 Super or the NVIDIA GeForce RTX 5060 Ti 16GB?
At 8k context both run the same 41 models we track fully in memory.
Which is faster for local AI, the NVIDIA GeForce RTX 4080 Super or the NVIDIA GeForce RTX 5060 Ti 16GB?
On the models both run fully in memory, the NVIDIA GeForce RTX 4080 Super is about 1.6× as fast as the NVIDIA GeForce RTX 5060 Ti 16GB (estimated, median across models).
What is the price difference between the NVIDIA GeForce RTX 4080 Super and the NVIDIA GeForce RTX 5060 Ti 16GB?
In Canada the NVIDIA GeForce RTX 4080 Super costs $1,599 at eBay (used) and the NVIDIA GeForce RTX 5060 Ti 16GB $1,120 at Amazon: the NVIDIA GeForce RTX 5060 Ti 16GB is $479 cheaper.

More comparisons