readygpu

NVIDIA GeForce RTX 3090 Ti vs NVIDIA Tesla P40

For running models locally, priced in the UK. At 64k context the first runs 22 models fully in memory, the second 22.

In short

Both have 24 GB of memory for models; the NVIDIA GeForce RTX 3090 Ti has 1,008 GB/s of bandwidth and the NVIDIA Tesla P40 346 GB/s. At 64k context both run the same 22 models we track fully in memory. On the models both run fully in memory, the NVIDIA GeForce RTX 3090 Ti is about 2.9× as fast as the NVIDIA Tesla P40 (estimated, median across models). In the UK the NVIDIA GeForce RTX 3090 Ti costs £2,199 at Amazon and the NVIDIA Tesla P40 £1,856 at Amazon: the NVIDIA Tesla P40 is £343 cheaper.

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

NVIDIA GeForce RTX 3090 Ti

£2,199

Amazon

Add to build
NVIDIA Tesla P40

£1,856

Amazon

Add to build

Specifications

SpecNVIDIA GeForce RTX 3090 TiNVIDIA Tesla P40
GPUGeForce RTX 3090 TiTesla P40
Memory24 GB GDDR6X24 GB GDDR5
Memory bus384-bit384-bit
Memory bandwidth1,008 GB/s346 GB/s
FP16 compute80 TFLOPS11.8 TFLOPS
SoftwareCUDACUDA
Board power450 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 3090 TiNVIDIA Tesla P40
Qwen 3.8 27B30tok/sUD-Q4_K_M10tok/sUD-Q4_K_M
Qwen 3.6 27B26tok/sQ5_K_M9tok/sQ5_K_M
Qwen 3.6 35B-A3B115tok/sUD-Q4_K_M40tok/sUD-Q4_K_M
Qwen 3.5 27B30tok/sQ4_K_M10tok/sQ4_K_M
Gemma 4 26B-A4B78tok/sUD-Q5_K_M27tok/sUD-Q5_K_M
Qwen 3.5 35B-A3B116tok/sQ4_K_M40tok/sQ4_K_M
GLM 4.7 Flash57tok/sQ4_K_M20tok/sQ4_K_M
gpt-oss 20B93tok/sMXFP432tok/sMXFP4
Gemma 4 12B44tok/sQ8_015tok/sQ8_0
Qwen 3.5 9B53tok/sQ8_018tok/sQ8_0
Gemma 3 27B28tok/sQ4_K_M10tok/sQ4_K_M
Ministral 3 14B29tok/sQ6_K10tok/sQ6_K
Qwen3 14B27tok/sQ6_K9tok/sQ6_K
DeepSeek R1 0528 Qwen3 8B34tok/sQ8_012tok/sQ8_0
Qwen3 8B34tok/sQ8_012tok/sQ8_0
Phi-4 14B26tok/sQ5_K_M9tok/sQ5_K_M
Qwen 3.5 4B94tok/sQ8_032tok/sQ8_0
Ministral 3 8B34tok/sQ8_012tok/sQ8_0
Granite 4.2 8B31tok/sQ8_011tok/sQ8_0
Gemma 4 E4B62tok/sQ8_021tok/sQ8_0
LFM2.5 8B-A1B88tok/sQ8_030tok/sQ8_0
Llama 3.1 8B41tok/sQ6_K14tok/sQ6_K
Qwen 3.5 122B-A10Boffloadoffload
Gemma 4 31Boffloadoffload
Qwen3 Coder Nextoffloadoffload
Mistral Small 4 119Boffloadoffload
Devstral Small 2 24Boffloadoffload
Qwen3 Next 80B-A3Boffloadoffload
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 Coder 30B-A3Boffloadoffload
Qwen3 32Boffloadoffload
Mistral Small 3.2 24Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
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
GLM 4.5 Airwon't runwon't run
Llama 3.3 70Bwon't runwon't run

Questions

Which is better for local AI, the NVIDIA GeForce RTX 3090 Ti or the NVIDIA Tesla P40?
Choose the NVIDIA GeForce RTX 3090 Ti for speed. Choose the NVIDIA Tesla P40 to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 3090 Ti or the NVIDIA Tesla P40?
At 64k context both run the same 22 models we track fully in memory.
Which is faster for local AI, the NVIDIA GeForce RTX 3090 Ti or the NVIDIA Tesla P40?
On the models both run fully in memory, the NVIDIA GeForce RTX 3090 Ti is about 2.9× as fast as the NVIDIA Tesla P40 (estimated, median across models).
What is the price difference between the NVIDIA GeForce RTX 3090 Ti and the NVIDIA Tesla P40?
In the UK the NVIDIA GeForce RTX 3090 Ti costs £2,199 at Amazon and the NVIDIA Tesla P40 £1,856 at Amazon: the NVIDIA Tesla P40 is £343 cheaper.

More comparisons