readygpu

NVIDIA RTX PRO 2000 Blackwell vs NVIDIA Tesla P40

For running models locally, priced in the US. At 64k context the first runs 32 models fully in memory, the second 49.

In short

The NVIDIA Tesla P40 has more memory for models: 24 GB against 16 GB. At 64k context the NVIDIA Tesla P40 runs 49 of the models we track fully in memory and the NVIDIA RTX PRO 2000 Blackwell 32; only the NVIDIA Tesla P40 holds Qwen 3.8 27B. On the models both run fully in memory, the NVIDIA Tesla P40 is about 1.2× as fast as the NVIDIA RTX PRO 2000 Blackwell (estimated, median across models). In the US the NVIDIA RTX PRO 2000 Blackwell costs $1,580 at eBay and the NVIDIA Tesla P40 $350 at eBay: the NVIDIA Tesla P40 is $1,230 cheaper.

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

NVIDIA RTX PRO 2000 Blackwell

$1,580

eBay

Add to build
NVIDIA Tesla P40

$350

eBay

Add to build

Specifications

SpecNVIDIA RTX PRO 2000 BlackwellNVIDIA Tesla P40
GPURTX PRO 2000 BlackwellTesla P40
Memory16 GB GDDR724 GB GDDR5
Memory bus128-bit384-bit
Memory bandwidth288 GB/s346 GB/s
FP16 compute17.03 TFLOPS11.8 TFLOPS
SoftwareCUDACUDA
Board power70 W250 W
PCIe generationGen 5Gen 3
PCIe lanesx8x16

What each runs

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

ModelNVIDIA RTX PRO 2000 BlackwellNVIDIA Tesla P40
Qwen 3.8 27Boffload10tok/sQ4_K_M
Qwen 3.6 27Boffload9tok/sQ5_K_M
Qwen 3.6 35B-A3Boffload39tok/sQ4_K_M
Qwen 3.5 27Boffload10tok/sQ4_K_M
Gemma 4 26B-A4Boffload27tok/sUD-Q5_K_M
Qwen 3.5 35B-A3Boffload40tok/sQ4_K_M
GLM 4.7 Flashoffload20tok/sQ4_K_M
Nemotron 3.5 Lightning 30B-A3Boffload49tok/sMXFP4
gpt-oss 20B27tok/sMXFP432tok/sMXFP4
Gemma 4 12B13tok/sQ8_015tok/sQ8_0
Qwen 3.5 9B15tok/sQ8_018tok/sQ8_0
Gemma 3 27Boffload10tok/sQ4_K_M
Ministral 3 14Boffload10tok/sQ6_K
Qwen3 14Boffload9tok/sQ6_K
DeepSeek R1 0528 Qwen3 8B12tok/sQ4_K_M12tok/sQ8_0
Qwen3 8B12tok/sQ4_K_M12tok/sQ8_0
Phi-4 14Boffload9tok/sQ5_K_M
Qwen 3.5 4B27tok/sQ8_032tok/sQ8_0
Ministral 3 8B12tok/sQ5_K_M12tok/sQ8_0
Granite 4.2 8Boffload11tok/sQ8_0
Gemma 4 E4B18tok/sQ8_021tok/sQ8_0
LFM2.5 8B-A1B25tok/sQ8_030tok/sQ8_0
Llama 3.1 8B12tok/sQ6_K14tok/sQ6_K
Qwen2.5 0.5B134tok/sQ8_0161tok/sQ8_0
Qwen3.5 0.8B109tok/sQ8_0131tok/sQ8_0
Qwen3.5 2B79tok/sQ5_K_M95tok/sQ5_K_M
LFM3 1.7B67tok/sQ8_081tok/sQ8_0
DeepSeek R1 Distill Qwen 1.5B47tok/sQ8_057tok/sQ8_0
MiniCPM5 2B33tok/sQ8_039tok/sQ8_0
Spark X2.5 4B32tok/smlx-4bit39tok/smlx-4bit
Mellum2.1 12B A2.5B Thinking29tok/sQ8_035tok/sQ8_0
Kimi VL A3B Thinking 250627tok/sQ4_K_M25tok/sQ8_0
FrogNano 4B 260926tok/sQ8_032tok/sQ8_0
LFM2.5 2.6B26tok/sQ8_031tok/sQ8_0
LFM2.5 VL 3B26tok/sQ8_031tok/sQ8_0
Kimi VL A3B26tok/smlx-5bit24tok/smlx-8bit
granite vision 4.1 4b20tok/sQ8_024tok/sQ8_0
granite 4.2 3b19tok/sQ8_023tok/sQ8_0
Ministral 3 3B Instruct 251217tok/sQ8_020tok/sQ8_0
GLM 4 9B 041416tok/smlx-5bit20tok/smlx-5bit
DeepSeek R1 Distill Qwen 7B15tok/sQ8_018tok/sQ8_0
GLM 4.6V Flash14tok/sQ8_017tok/sQ8_0
GLM 4.1V 9B Thinking12tok/smlx-8bit15tok/smlx-8bit
DeepSeek R1 Distill Llama 8B12tok/sQ6_K13tok/sQ8_0
Ministral 3 8B Reasoning 251212tok/sQ5_K_M12tok/sQ8_0
LFM2.5 24B A2Boffload19tok/sQ5_K_M
Muse Glimmer 30Boffload10tok/sQ5_K_M
Ministral 3 14B Reasoning 2512offload10tok/sQ6_K
DeepSeek R1 Distill Qwen 14Boffload9tok/sQ5_K_M
Qwen 3.5 122B-A10Bwon't runoffload
Gemma 4 31Boffloadoffload
Qwen3 Coder Nextwon't runoffload
Mistral Small 4 119Boffloadoffload
Devstral Small 2 24Boffloadoffload
Qwen3 Next 80B-A3Bwon't runoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 Coder 30B-A3Boffloadoffload
Qwen3 32Boffloadoffload
Mistral Small 3.2 24Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
Devstral Small 2507offloadoffload
Magistral Small 2506offloadoffload
Magistral Small 2507offloadoffload
Magistral Small 2509offloadoffload
Qwen3.8 27B OBLITERATEDoffloadoffload
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
gpt-oss 120Bwon't runwon't run
GLM 4.5 Airwon'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 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 RTX PRO 2000 Blackwell or the NVIDIA Tesla P40?
Choose the NVIDIA Tesla P40 to run bigger models. Choose the NVIDIA Tesla P40 for speed. Choose the NVIDIA Tesla P40 to spend less.
Which can run bigger models, the NVIDIA RTX PRO 2000 Blackwell or the NVIDIA Tesla P40?
At 64k context the NVIDIA Tesla P40 runs 49 of the models we track fully in memory and the NVIDIA RTX PRO 2000 Blackwell 32; only the NVIDIA Tesla P40 holds Qwen 3.8 27B.
Which is faster for local AI, the NVIDIA RTX PRO 2000 Blackwell or the NVIDIA Tesla P40?
On the models both run fully in memory, the NVIDIA Tesla P40 is about 1.2× as fast as the NVIDIA RTX PRO 2000 Blackwell (estimated, median across models).
What is the price difference between the NVIDIA RTX PRO 2000 Blackwell and the NVIDIA Tesla P40?
In the US the NVIDIA RTX PRO 2000 Blackwell costs $1,580 at eBay and the NVIDIA Tesla P40 $350 at eBay: the NVIDIA Tesla P40 is $1,230 cheaper.

More comparisons

More hardware for local AI