readygpu

NVIDIA GeForce RTX 4070 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 4070 35; only the NVIDIA Tesla P40 holds Qwen 3.8 27B. On the models both run fully in memory, the NVIDIA GeForce RTX 4070 is about 1.5× as fast as the NVIDIA Tesla P40 (estimated, median across models). In the UK the NVIDIA GeForce RTX 4070 costs £786 at Amazon and the NVIDIA Tesla P40 £783 at Amazon: the NVIDIA Tesla P40 is £3 cheaper.

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

NVIDIA GeForce RTX 4070

£786

Amazon

Add to build
NVIDIA Tesla P40

£783

Amazon

Add to build

Specifications

SpecNVIDIA GeForce RTX 4070NVIDIA Tesla P40
GPUGeForce RTX 4070Tesla P40
Memory12 GB GDDR6X24 GB GDDR5
Memory bus192-bit384-bit
Memory bandwidth504.2 GB/s346 GB/s
FP16 compute29.146 TFLOPS11.8 TFLOPS
SoftwareCUDACUDA
Board power200 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 4070NVIDIA 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 12B31tok/sQ6_K16tok/sQ8_0
Qwen 3.5 9B32tok/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 14B30tok/sQ4_K_M13tok/sQ8_0
Ministral 3 14B29tok/sQ5_K_M14tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B32tok/sQ8_022tok/sQ8_0
Qwen3 8B32tok/sQ8_022tok/sQ8_0
Phi-4 14B30tok/sQ4_K_M12tok/sQ8_0
Qwen 3.5 4B65tok/sQ8_045tok/sQ8_0
Ministral 3 8B31tok/sQ8_021tok/sQ8_0
Granite 4.2 8B29tok/sQ8_020tok/sQ8_0
Gemma 4 E4B37tok/sQ8_025tok/sQ8_0
LFM2.5 8B-A1B128tok/sQ8_088tok/sQ8_0
Llama 3.1 8B41tok/sQ6_K28tok/sQ6_K
Qwen2.5 0.5B495tok/sQ8_0340tok/sQ8_0
Qwen3.5 0.8B336tok/sQ8_0230tok/sQ8_0
Qwen3.5 2B201tok/sQ5_K_M138tok/sQ5_K_M
LFM3 1.7B160tok/sQ8_0110tok/sQ8_0
DeepSeek R1 Distill Qwen 1.5B147tok/sQ8_0101tok/sQ8_0
MiniCPM5 2B103tok/sQ8_071tok/sQ8_0
LFM2.5 2.6B93tok/sQ8_064tok/sQ8_0
LFM2.5 VL 3B93tok/sQ8_064tok/sQ8_0
Spark X2.5 4B92tok/smlx-4bit63tok/smlx-4bit
Kimi VL A3B Thinking 250686tok/sQ4_K_M38tok/sQ8_0
Mellum2.1 12B A2.5B Thinking85tok/sQ5_K_M46tok/sQ8_0
granite vision 4.1 4b73tok/sQ8_050tok/sQ8_0
Ministral 3 3B Instruct 251269tok/sQ8_047tok/sQ8_0
granite 4.2 3b69tok/sQ8_047tok/sQ8_0
FrogNano 4B 260963tok/sQ8_043tok/sQ8_0
DeepSeek R1 Distill Qwen 7B37tok/sQ8_025tok/sQ8_0
GLM 4 9B 041436tok/smlx-5bit25tok/smlx-5bit
DeepSeek R1 Distill Llama 8B33tok/sQ8_022tok/sQ8_0
Ministral 3 8B Reasoning 251231tok/sQ8_021tok/sQ8_0
GLM 4.6V Flash30tok/sQ8_021tok/sQ8_0
DeepSeek R1 Distill Qwen 14B30tok/sQ4_K_M12tok/sQ8_0
Ministral 3 14B Reasoning 251229tok/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 4070 or the NVIDIA Tesla P40?
Choose the NVIDIA Tesla P40 to run bigger models. Choose the NVIDIA GeForce RTX 4070 for speed. Choose the NVIDIA Tesla P40 to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 4070 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 4070 35; only the NVIDIA Tesla P40 holds Qwen 3.8 27B.
Which is faster for local AI, the NVIDIA GeForce RTX 4070 or the NVIDIA Tesla P40?
On the models both run fully in memory, the NVIDIA GeForce RTX 4070 is about 1.5× as fast as the NVIDIA Tesla P40 (estimated, median across models).
What is the price difference between the NVIDIA GeForce RTX 4070 and the NVIDIA Tesla P40?
In the UK the NVIDIA GeForce RTX 4070 costs £786 at Amazon and the NVIDIA Tesla P40 £783 at Amazon: the NVIDIA Tesla P40 is £3 cheaper.

More comparisons

More hardware for local AI