readygpu

NVIDIA GeForce RTX 4080 Super vs NVIDIA Tesla P40

For running models locally, priced in the UK. At 8k context the first runs 39 models fully in memory, the second 53.

In short

The NVIDIA Tesla P40 has more memory for models: 24 GB against 16 GB. At 8k context the NVIDIA Tesla P40 runs 53 of the models we track fully in memory and the NVIDIA GeForce RTX 4080 Super 39; only the NVIDIA Tesla P40 holds Qwen 3.8 27B. On the models both run fully in memory, the NVIDIA GeForce RTX 4080 Super is about 2.1× as fast as the NVIDIA Tesla P40 (estimated, median across models). In the UK the NVIDIA GeForce RTX 4080 Super costs £1,604 at Amazon and the NVIDIA Tesla P40 £1,838 at Amazon: the NVIDIA GeForce RTX 4080 Super is £233 cheaper.

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

NVIDIA GeForce RTX 4080 Super

£1,604

Amazon

Add to build
NVIDIA Tesla P40

£1,838

Amazon

Add to build

Specifications

SpecNVIDIA GeForce RTX 4080 SuperNVIDIA Tesla P40
GPUGeForce RTX 4080 SuperTesla P40
Memory16 GB GDDR6X24 GB GDDR5
Memory bus256-bit384-bit
Memory bandwidth736 GB/s346 GB/s
FP16 compute104 TFLOPS11.8 TFLOPS
SoftwareCUDACUDA
Board power320 W250 W
PCIe generationGen 4Gen 3
PCIe lanesx16x16

What each runs

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

ModelNVIDIA GeForce RTX 4080 SuperNVIDIA Tesla P40
Qwen 3.8 27Boffload10tok/sUD-Q6_K
Qwen 3.6 27Boffload9tok/sQ6_K
Gemma 4 31Boffload9tok/sQ5_K_M
Qwen 3.6 35B-A3Boffload62tok/sQ4_K_M
Qwen 3.5 27Boffload9tok/sQ6_K
Gemma 4 26B-A4Boffload32tok/sUD-Q6_K
Devstral Small 2 24B29tok/sQ4_K_M10tok/sQ6_K
Qwen 3.5 35B-A3Boffload62tok/sQ4_K_M
GLM 4.7 Flashoffload32tok/sQ5_K_M
gpt-oss 20B104tok/sMXFP449tok/sMXFP4
Qwen3 Coder 30B-A3Boffload44tok/sQ5_K_M
Qwen3 32Boffload10tok/sQ4_K_M
Gemma 4 12B35tok/sQ8_016tok/sQ8_0
Qwen 3.5 9B46tok/sQ8_022tok/sQ8_0
Mistral Small 3.2 24B29tok/sQ4_K_M10tok/sQ6_K
Gemma 3 27Boffload9tok/sQ6_K
DeepSeek R1 Distill Qwen 32Boffload10tok/sQ4_K_M
Qwen3 14B34tok/sQ6_K13tok/sQ8_0
Ministral 3 14B29tok/sQ8_014tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B46tok/sQ8_022tok/sQ8_0
Qwen3 8B46tok/sQ8_022tok/sQ8_0
Phi-4 14B33tok/sQ6_K12tok/sQ8_0
Qwen 3.5 4B95tok/sQ8_045tok/sQ8_0
Ministral 3 8B45tok/sQ8_021tok/sQ8_0
Granite 4.2 8B43tok/sQ8_020tok/sQ8_0
Gemma 4 E4B54tok/sQ8_025tok/sQ8_0
LFM2.5 8B-A1B187tok/sQ8_088tok/sQ8_0
Llama 3.1 8B60tok/sQ6_K28tok/sQ6_K
Qwen2.5 0.5B722tok/sQ8_0340tok/sQ8_0
Qwen3.5 0.8B490tok/sQ8_0230tok/sQ8_0
Qwen3.5 2B294tok/sQ5_K_M138tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B214tok/sQ8_0101tok/sQ8_0
MiniCPM5 2B151tok/sQ8_071tok/sQ8_0
LFM2.5 2.6B135tok/sQ8_064tok/sQ8_0
LFM2.5 VL 3B135tok/sQ8_064tok/sQ8_0
Kimi VL A3B Thinking 2506126tok/sQ4_K_M38tok/sQ8_0
granite vision 4.1 4b106tok/sQ8_050tok/sQ8_0
granite 4.2 3b100tok/sQ8_047tok/sQ8_0
Kimi VL A3B98tok/smlx-6bit37tok/smlx-8bit
Mellum2.1 12B A2.5B Thinking97tok/sQ8_046tok/sQ8_0
DeepSeek R1 Distill Qwen 7B53tok/sQ8_025tok/sQ8_0
GLM 4 9B 041453tok/smlx-5bit25tok/smlx-5bit
DeepSeek R1 Distill Llama 8B48tok/sQ8_022tok/sQ8_0
Ministral 3 8B Reasoning 251245tok/sQ8_021tok/sQ8_0
GLM 4.6V Flash44tok/sQ8_021tok/sQ8_0
GLM 4.1V 9B Thinking38tok/smlx-8bit18tok/smlx-8bit
DeepSeek R1 Distill Qwen 14B33tok/sQ6_K12tok/sQ8_0
Devstral Small 250729tok/sQ4_K_M12tok/sQ5_K_M
Magistral Small 250629tok/sQ4_K_M10tok/sQ6_K
Magistral Small 250729tok/sQ4_K_M12tok/sQ5_K_M
Magistral Small 250929tok/sQ4_K_M12tok/sQ5_K_M
LFM2.5 24B A2Boffload53tok/sQ6_K
granite 4.2 30boffload9tok/sQ5_K_M
Qwen 3.5 122B-A10Boffloadoffload
Qwen3 Coder Nextwon't runoffload
Mistral Small 4 119Boffloadoffload
GLM 4.5 Airwon't runoffload
Qwen3 Next 80B-A3Bwon't runoffload
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
Kimi Linear 48B-A3Boffloadoffload
Llama 3.3 70Bwon't runoffload
DeepSeek R1 Distill Llama 70Bwon't runoffload
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
DeepSeek R1won't runwon't run
DeepSeek R1 0528won'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 4080 Super or the NVIDIA Tesla P40?
Choose the NVIDIA Tesla P40 to run bigger models. Choose the NVIDIA GeForce RTX 4080 Super for speed. Choose the NVIDIA GeForce RTX 4080 Super to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 4080 Super or the NVIDIA Tesla P40?
At 8k context the NVIDIA Tesla P40 runs 53 of the models we track fully in memory and the NVIDIA GeForce RTX 4080 Super 39; only the NVIDIA Tesla P40 holds Qwen 3.8 27B.
Which is faster for local AI, the NVIDIA GeForce RTX 4080 Super or the NVIDIA Tesla P40?
On the models both run fully in memory, the NVIDIA GeForce RTX 4080 Super is about 2.1× as fast as the NVIDIA Tesla P40 (estimated, median across models).
What is the price difference between the NVIDIA GeForce RTX 4080 Super and the NVIDIA Tesla P40?
In the UK the NVIDIA GeForce RTX 4080 Super costs £1,604 at Amazon and the NVIDIA Tesla P40 £1,838 at Amazon: the NVIDIA GeForce RTX 4080 Super is £233 cheaper.

More comparisons