readygpu

NVIDIA GeForce RTX 4070 Ti Super vs NVIDIA GeForce RTX 5080

For running models locally, priced in the UK. At 8k context the first runs 39 models fully in memory, the second 39.

In short

Both have 16 GB of memory for models; the NVIDIA GeForce RTX 4070 Ti Super has 672 GB/s of bandwidth and the NVIDIA GeForce RTX 5080 960 GB/s. At 8k context both run the same 39 models we track fully in memory. On the models both run fully in memory, the NVIDIA GeForce RTX 5080 is about 1.4× as fast as the NVIDIA GeForce RTX 4070 Ti Super (estimated, median across models). In the UK the NVIDIA GeForce RTX 4070 Ti Super costs £1,329 at Amazon and the NVIDIA GeForce RTX 5080 £1,199 at eBay: the NVIDIA GeForce RTX 5080 is £130 cheaper.

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

NVIDIA GeForce RTX 4070 Ti Super

£1,329

Amazon

Add to build
NVIDIA GeForce RTX 5080

£1,199

eBay

Add to build

Specifications

SpecNVIDIA GeForce RTX 4070 Ti SuperNVIDIA GeForce RTX 5080
GPUGeForce RTX 4070 Ti SuperGeForce RTX 5080
Memory16 GB GDDR6X16 GB GDDR7
Memory bus256-bit256-bit
Memory bandwidth672 GB/s960 GB/s
FP16 compute88 TFLOPS113 TFLOPS
SoftwareCUDACUDA
Board power285 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 4070 Ti SuperNVIDIA GeForce RTX 5080
Devstral Small 2 24B27tok/sQ4_K_M38tok/sQ4_K_M
gpt-oss 20B95tok/sMXFP4136tok/sMXFP4
Gemma 4 12B32tok/sQ8_045tok/sQ8_0
Qwen 3.5 9B42tok/sQ8_060tok/sQ8_0
Mistral Small 3.2 24B27tok/sQ4_K_M38tok/sQ4_K_M
Qwen3 14B31tok/sQ6_K44tok/sQ6_K
Ministral 3 14B27tok/sQ8_038tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B42tok/sQ8_060tok/sQ8_0
Qwen3 8B42tok/sQ8_060tok/sQ8_0
Phi-4 14B30tok/sQ6_K43tok/sQ6_K
Qwen 3.5 4B87tok/sQ8_0124tok/sQ8_0
Ministral 3 8B41tok/sQ8_059tok/sQ8_0
Granite 4.2 8B39tok/sQ8_056tok/sQ8_0
Gemma 4 E4B49tok/sQ8_070tok/sQ8_0
LFM2.5 8B-A1B170tok/sQ8_0244tok/sQ8_0
Llama 3.1 8B54tok/sQ6_K78tok/sQ6_K
Qwen2.5 0.5B660tok/sQ8_0942tok/sQ8_0
Qwen3.5 0.8B447tok/sQ8_0639tok/sQ8_0
Qwen3.5 2B268tok/sQ5_K_M383tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B196tok/sQ8_0280tok/sQ8_0
MiniCPM5 2B137tok/sQ8_0196tok/sQ8_0
LFM2.5 2.6B123tok/sQ8_0176tok/sQ8_0
LFM2.5 VL 3B123tok/sQ8_0176tok/sQ8_0
Kimi VL A3B Thinking 2506115tok/sQ4_K_M164tok/sQ4_K_M
granite vision 4.1 4b97tok/sQ8_0139tok/sQ8_0
granite 4.2 3b91tok/sQ8_0130tok/sQ8_0
Kimi VL A3B90tok/smlx-6bit128tok/smlx-6bit
Mellum2.1 12B A2.5B Thinking89tok/sQ8_0127tok/sQ8_0
DeepSeek R1 Distill Qwen 7B49tok/sQ8_070tok/sQ8_0
GLM 4 9B 041449tok/smlx-5bit69tok/smlx-5bit
DeepSeek R1 Distill Llama 8B43tok/sQ8_062tok/sQ8_0
Ministral 3 8B Reasoning 251241tok/sQ8_059tok/sQ8_0
GLM 4.6V Flash40tok/sQ8_058tok/sQ8_0
GLM 4.1V 9B Thinking34tok/smlx-8bit49tok/smlx-8bit
DeepSeek R1 Distill Qwen 14B30tok/sQ6_K43tok/sQ6_K
Devstral Small 250727tok/sQ4_K_M38tok/sQ4_K_M
Magistral Small 250627tok/sQ4_K_M38tok/sQ4_K_M
Magistral Small 250727tok/sQ4_K_M38tok/sQ4_K_M
Magistral Small 250927tok/sQ4_K_M38tok/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
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 4.5Vwon'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 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 4070 Ti Super or the NVIDIA GeForce RTX 5080?
Choose the NVIDIA GeForce RTX 5080 for speed. Choose the NVIDIA GeForce RTX 5080 to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 4070 Ti Super or the NVIDIA GeForce RTX 5080?
At 8k context both run the same 39 models we track fully in memory.
Which is faster for local AI, the NVIDIA GeForce RTX 4070 Ti Super or the NVIDIA GeForce RTX 5080?
On the models both run fully in memory, the NVIDIA GeForce RTX 5080 is about 1.4× as fast as the NVIDIA GeForce RTX 4070 Ti Super (estimated, median across models).
What is the price difference between the NVIDIA GeForce RTX 4070 Ti Super and the NVIDIA GeForce RTX 5080?
In the UK the NVIDIA GeForce RTX 4070 Ti Super costs £1,329 at Amazon and the NVIDIA GeForce RTX 5080 £1,199 at eBay: the NVIDIA GeForce RTX 5080 is £130 cheaper.

More comparisons