readygpu

NVIDIA RTX PRO 4500 Blackwell vs NVIDIA Tesla P40

For running models locally, priced in Germany. At 8k context the first runs 61 models fully in memory, the second 60.

In short

The NVIDIA RTX PRO 4500 Blackwell has more memory for models: 32 GB against 24 GB. At 8k context the NVIDIA RTX PRO 4500 Blackwell runs 61 of the models we track fully in memory and the NVIDIA Tesla P40 60; only the NVIDIA RTX PRO 4500 Blackwell holds Kimi Linear 48B-A3B. On the models both run fully in memory, the NVIDIA RTX PRO 4500 Blackwell is about 2.6× as fast as the NVIDIA Tesla P40 (estimated, median across models).

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

NVIDIA RTX PRO 4500 Blackwell

Not priced here

Add to build
NVIDIA Tesla P40

369 €

eBay, used (asking)

Add to build

Specifications

SpecNVIDIA RTX PRO 4500 BlackwellNVIDIA Tesla P40
GPURTX PRO 4500 BlackwellTesla P40
Memory32 GB GDDR724 GB GDDR5
Memory bus256-bit384-bit
Memory bandwidth896 GB/s346 GB/s
FP16 compute54.94 TFLOPS11.8 TFLOPS
SoftwareCUDACUDA
Board power200 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 RTX PRO 4500 BlackwellNVIDIA Tesla P40
Qwen 3.8 27B19tok/sQ8_010tok/sUD-Q6_K
Qwen 3.6 27B19tok/sQ8_09tok/sQ6_K
Gemma 4 31B21tok/sQ6_K9tok/sQ5_K_M
Qwen 3.6 35B-A3B119tok/sQ6_K62tok/sQ4_K_M
Qwen 3.5 27B19tok/sQ8_09tok/sQ6_K
Gemma 4 26B-A4B73tok/sQ8_032tok/sUD-Q6_K
Qwen 3.5 35B-A3B126tok/sQ6_K62tok/sQ4_K_M
GLM 4.7 Flash58tok/sQ8_032tok/sQ5_K_M
Devstral Small 2 24B21tok/sQ8_010tok/sQ6_K
Nemotron 3.5 Lightning 30B-A3B112tok/sUD-Q5_K_M56tok/sMXFP4
Kimi Linear 48B-A3B172tok/sQ4_K_Moffload
gpt-oss 20B127tok/sMXFP449tok/sMXFP4
Qwen3 Coder 30B-A3B102tok/sQ6_K44tok/sQ5_K_M
Qwen3 32B19tok/sQ6_K10tok/sQ4_K_M
Gemma 4 12B42tok/sQ8_016tok/sQ8_0
Qwen 3.5 9B56tok/sQ8_022tok/sQ8_0
Mistral Small 3.2 24B21tok/sQ8_010tok/sQ6_K
DeepSeek R1 Distill Qwen 32B19tok/sQ6_K10tok/sQ4_K_M
Gemma 3 27B19tok/sQ8_09tok/sQ6_K
Ministral 3 14B35tok/sQ8_014tok/sQ8_0
Qwen3 14B33tok/sQ8_013tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B56tok/sQ8_022tok/sQ8_0
Qwen3 8B56tok/sQ8_022tok/sQ8_0
Phi-4 14B32tok/sQ8_012tok/sQ8_0
Qwen 3.5 4B116tok/sQ8_045tok/sQ8_0
Ministral 3 8B55tok/sQ8_021tok/sQ8_0
Granite 4.2 8B52tok/sQ8_020tok/sQ8_0
Gemma 4 E4B66tok/sQ8_025tok/sQ8_0
LFM2.5 8B-A1B227tok/sQ8_088tok/sQ8_0
Llama 3.1 8B72tok/sQ6_K28tok/sQ6_K
Qwen2.5 0.5B879tok/sQ8_0340tok/sQ8_0
Qwen3.5 0.8B596tok/sQ8_0230tok/sQ8_0
Qwen3.5 2B357tok/sQ5_K_M138tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B261tok/sQ8_0101tok/sQ8_0
MiniCPM5 2B183tok/sQ8_071tok/sQ8_0
LFM2.5 2.6B164tok/sQ8_064tok/sQ8_0
LFM2.5 VL 3B164tok/sQ8_064tok/sQ8_0
Spark X2.5 4B163tok/smlx-4bit63tok/smlx-4bit
granite vision 4.1 4b130tok/sQ8_050tok/sQ8_0
Ministral 3 3B Instruct 2512123tok/sQ8_047tok/sQ8_0
granite 4.2 3b122tok/sQ8_047tok/sQ8_0
LFM2.5 24B A2B119tok/sQ8_053tok/sQ6_K
Mellum2.1 12B A2.5B Thinking118tok/sQ8_046tok/sQ8_0
FrogNano 4B 2609112tok/sQ8_043tok/sQ8_0
Kimi VL A3B Thinking 250699tok/sQ8_038tok/sQ8_0
Kimi VL A3B95tok/smlx-8bit37tok/smlx-8bit
DeepSeek R1 Distill Qwen 7B65tok/sQ8_025tok/sQ8_0
GLM 4 9B 041465tok/smlx-5bit25tok/smlx-5bit
DeepSeek R1 Distill Llama 8B58tok/sQ8_022tok/sQ8_0
Ministral 3 8B Reasoning 251255tok/sQ8_021tok/sQ8_0
GLM 4.6V Flash54tok/sQ8_021tok/sQ8_0
GLM 4.1V 9B Thinking46tok/smlx-8bit18tok/smlx-8bit
Ministral 3 14B Reasoning 251235tok/sQ8_014tok/sQ8_0
DeepSeek R1 Distill Qwen 14B32tok/sQ8_012tok/sQ8_0
Qwen3.8 27B OBLITERATED26tok/smlx-4bit10tok/smlx-4bit
Devstral Small 250721tok/sQ8_012tok/sQ5_K_M
Magistral Small 250621tok/sQ8_010tok/sQ6_K
Magistral Small 250721tok/sQ8_012tok/sQ5_K_M
Magistral Small 250921tok/sQ8_012tok/sQ5_K_M
granite 4.2 30b21tok/sQ6_K9tok/sQ5_K_M
Muse Glimmer 30B17tok/sQ8_09tok/sQ6_K
Qwen 3.5 122B-A10Boffloadoffload
Qwen3 Coder Nextoffloadoffload
Nemotron 3 Super 120B-A12Boffloadwon't run
Mistral Small 4 119Boffloadoffload
GLM 4.5 Airoffloadoffload
Qwen3 Next 80B-A3Boffloadoffload
Llama 3.3 70Boffloadoffload
DeepSeek R1 Distill Llama 70Boffloadoffload
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
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 RTX PRO 4500 Blackwell or the NVIDIA Tesla P40?
Choose the NVIDIA RTX PRO 4500 Blackwell to run bigger models. Choose the NVIDIA RTX PRO 4500 Blackwell for speed.
Which can run bigger models, the NVIDIA RTX PRO 4500 Blackwell or the NVIDIA Tesla P40?
At 8k context the NVIDIA RTX PRO 4500 Blackwell runs 61 of the models we track fully in memory and the NVIDIA Tesla P40 60; only the NVIDIA RTX PRO 4500 Blackwell holds Kimi Linear 48B-A3B.
Which is faster for local AI, the NVIDIA RTX PRO 4500 Blackwell or the NVIDIA Tesla P40?
On the models both run fully in memory, the NVIDIA RTX PRO 4500 Blackwell is about 2.6× as fast as the NVIDIA Tesla P40 (estimated, median across models).

More comparisons

More hardware for local AI