readygpu

NVIDIA GeForce RTX 5070 vs NVIDIA Tesla P40

For running models locally, priced in the UK. At 8k context the first runs 35 models fully in memory, the second 61.

In short

The NVIDIA Tesla P40 has more memory for models: 24 GB against 12 GB. At 8k context the NVIDIA Tesla P40 runs 61 of the models we track fully in memory and the NVIDIA GeForce RTX 5070 35; only the NVIDIA Tesla P40 holds Qwen 3.8 27B. On the models both run fully in memory, the NVIDIA GeForce RTX 5070 is about 1.9× as fast as the NVIDIA Tesla P40 (estimated, median across models). In the UK the NVIDIA GeForce RTX 5070 costs £736 at eBay and the NVIDIA Tesla P40 £716 at Amazon: the NVIDIA Tesla P40 is £20 cheaper.

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

NVIDIA GeForce RTX 5070

£736

eBay

Add to build
NVIDIA Tesla P40

£716

Amazon

Add to build

Specifications

SpecNVIDIA GeForce RTX 5070NVIDIA Tesla P40
GPUGeForce RTX 5070Tesla P40
Memory12 GB GDDR724 GB GDDR5
Memory bus192-bit384-bit
Memory bandwidth672 GB/s346 GB/s
FP16 compute62 TFLOPS11.8 TFLOPS
SoftwareCUDACUDA
Board power250 W250 W
PCIe generationGen 5Gen 3
PCIe lanesx16x16

What each runs

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

ModelNVIDIA GeForce RTX 5070NVIDIA 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
Qwen 3.5 35B-A3Boffload62tok/sQ4_K_M
GLM 4.7 Flashoffload32tok/sQ5_K_M
Devstral Small 2 24Boffload10tok/sQ6_K
Nemotron 3.5 Lightning 30B-A3Boffload56tok/sMXFP4
gpt-oss 20Boffload49tok/sMXFP4
Qwen3 Coder 30B-A3Boffload44tok/sQ5_K_M
Qwen3 32Boffload10tok/sQ4_K_M
Gemma 4 12B41tok/sQ6_K16tok/sQ8_0
Qwen 3.5 9B42tok/sQ8_022tok/sQ8_0
Mistral Small 3.2 24Boffload10tok/sQ6_K
Gemma 3 27Boffload9tok/sQ6_K
DeepSeek R1 Distill Qwen 32Boffload10tok/sQ4_K_M
Qwen3 14B40tok/sQ4_K_M13tok/sQ8_0
Ministral 3 14B38tok/sQ5_K_M14tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B42tok/sQ8_022tok/sQ8_0
Qwen3 8B42tok/sQ8_022tok/sQ8_0
Phi-4 14B39tok/sQ4_K_M12tok/sQ8_0
Qwen 3.5 4B87tok/sQ8_045tok/sQ8_0
Ministral 3 8B41tok/sQ8_021tok/sQ8_0
Granite 4.2 8B39tok/sQ8_020tok/sQ8_0
Gemma 4 E4B49tok/sQ8_025tok/sQ8_0
LFM2.5 8B-A1B170tok/sQ8_088tok/sQ8_0
Llama 3.1 8B54tok/sQ6_K28tok/sQ6_K
Qwen2.5 0.5B660tok/sQ8_0340tok/sQ8_0
Qwen3.5 0.8B447tok/sQ8_0230tok/sQ8_0
Qwen3.5 2B268tok/sQ5_K_M138tok/sQ5_K_M
LFM3 1.7B213tok/sQ8_0110tok/sQ8_0
DeepSeek R1 Distill Qwen 1.5B196tok/sQ8_0101tok/sQ8_0
MiniCPM5 2B137tok/sQ8_071tok/sQ8_0
LFM2.5 2.6B123tok/sQ8_064tok/sQ8_0
LFM2.5 VL 3B123tok/sQ8_064tok/sQ8_0
Spark X2.5 4B123tok/smlx-4bit63tok/smlx-4bit
Kimi VL A3B Thinking 2506115tok/sQ4_K_M38tok/sQ8_0
Mellum2.1 12B A2.5B Thinking113tok/sQ5_K_M46tok/sQ8_0
granite vision 4.1 4b97tok/sQ8_050tok/sQ8_0
Ministral 3 3B Instruct 251292tok/sQ8_047tok/sQ8_0
granite 4.2 3b91tok/sQ8_047tok/sQ8_0
FrogNano 4B 260984tok/sQ8_043tok/sQ8_0
DeepSeek R1 Distill Qwen 7B49tok/sQ8_025tok/sQ8_0
GLM 4 9B 041449tok/smlx-5bit25tok/smlx-5bit
DeepSeek R1 Distill Llama 8B43tok/sQ8_022tok/sQ8_0
Ministral 3 8B Reasoning 251241tok/sQ8_021tok/sQ8_0
GLM 4.6V Flash40tok/sQ8_021tok/sQ8_0
DeepSeek R1 Distill Qwen 14B39tok/sQ4_K_M12tok/sQ8_0
Ministral 3 14B Reasoning 251238tok/sQ5_K_M14tok/sQ8_0
Kimi VL A3Boffload37tok/smlx-8bit
LFM2.5 24B A2Boffload53tok/sQ6_K
GLM 4.1V 9B Thinkingoffload18tok/smlx-8bit
Devstral Small 2507offload12tok/sQ5_K_M
Magistral Small 2506offload10tok/sQ6_K
Magistral Small 2507offload12tok/sQ5_K_M
Magistral Small 2509offload12tok/sQ5_K_M
Muse Glimmer 30Boffload9tok/sQ6_K
granite 4.2 30boffload9tok/sQ5_K_M
Qwen3.8 27B OBLITERATEDoffload10tok/smlx-4bit
Qwen 3.5 122B-A10Bwon't runoffload
Qwen3 Coder Nextwon't runoffload
Mistral Small 4 119Bwon't runoffload
GLM 4.5 Airwon't runoffload
Qwen3 Next 80B-A3Bwon't runoffload
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 V3won'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 5070 or the NVIDIA Tesla P40?
Choose the NVIDIA Tesla P40 to run bigger models. Choose the NVIDIA GeForce RTX 5070 for speed. Choose the NVIDIA Tesla P40 to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 5070 or the NVIDIA Tesla P40?
At 8k context the NVIDIA Tesla P40 runs 61 of the models we track fully in memory and the NVIDIA GeForce RTX 5070 35; only the NVIDIA Tesla P40 holds Qwen 3.8 27B.
Which is faster for local AI, the NVIDIA GeForce RTX 5070 or the NVIDIA Tesla P40?
On the models both run fully in memory, the NVIDIA GeForce RTX 5070 is about 1.9× as fast as the NVIDIA Tesla P40 (estimated, median across models).
What is the price difference between the NVIDIA GeForce RTX 5070 and the NVIDIA Tesla P40?
In the UK the NVIDIA GeForce RTX 5070 costs £736 at eBay and the NVIDIA Tesla P40 £716 at Amazon: the NVIDIA Tesla P40 is £20 cheaper.

More comparisons

More hardware for local AI