readygpu

NVIDIA RTX PRO 4500 Blackwell vs NVIDIA Tesla P40

For running models locally, priced in the US. At 64k context the first runs 58 models fully in memory, the second 48.

In short

The NVIDIA RTX PRO 4500 Blackwell has more memory for models: 32 GB against 24 GB. At 64k context the NVIDIA RTX PRO 4500 Blackwell runs 58 of the models we track fully in memory and the NVIDIA Tesla P40 48; only the NVIDIA RTX PRO 4500 Blackwell holds Gemma 4 31B. 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

$345

Amazon

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 27B20tok/sQ6_K10tok/sQ4_K_M
Qwen 3.6 27B21tok/sQ6_K9tok/sQ5_K_M
Gemma 4 31B18tok/sQ6_Koffload
Qwen 3.6 35B-A3B84tok/sQ6_K39tok/sQ4_K_M
Qwen 3.5 27B21tok/sQ6_K10tok/sQ4_K_M
Gemma 4 26B-A4B58tok/sQ8_027tok/sUD-Q5_K_M
Qwen 3.5 35B-A3B87tok/sQ6_K40tok/sQ4_K_M
GLM 4.7 Flash44tok/sQ6_K20tok/sQ4_K_M
Devstral Small 2 24B19tok/sQ6_Koffload
Nemotron 3.5 Lightning 30B-A3B100tok/sUD-Q5_K_M49tok/sMXFP4
Kimi Linear 48B-A3B139tok/sQ4_K_Moffload
gpt-oss 20B83tok/sMXFP432tok/sMXFP4
Qwen3 Coder 30B-A3B37tok/sQ6_Koffload
Gemma 4 12B40tok/sQ8_015tok/sQ8_0
Qwen 3.5 9B47tok/sQ8_018tok/sQ8_0
Gemma 3 27B20tok/sQ6_K10tok/sQ4_K_M
Mistral Small 3.2 24B19tok/sQ6_Koffload
Ministral 3 14B22tok/sQ8_010tok/sQ6_K
Qwen3 14B21tok/sQ8_09tok/sQ6_K
DeepSeek R1 0528 Qwen3 8B30tok/sQ8_012tok/sQ8_0
Qwen3 8B30tok/sQ8_012tok/sQ8_0
Phi-4 14B19tok/sQ8_09tok/sQ5_K_M
Qwen 3.5 4B83tok/sQ8_032tok/sQ8_0
Ministral 3 8B31tok/sQ8_012tok/sQ8_0
Granite 4.2 8B28tok/sQ8_011tok/sQ8_0
Gemma 4 E4B55tok/sQ8_021tok/sQ8_0
LFM2.5 8B-A1B78tok/sQ8_030tok/sQ8_0
Llama 3.1 8B37tok/sQ6_K14tok/sQ6_K
Qwen2.5 0.5B416tok/sQ8_0161tok/sQ8_0
Qwen3.5 0.8B340tok/sQ8_0131tok/sQ8_0
Qwen3.5 2B246tok/sQ5_K_M95tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B147tok/sQ8_057tok/sQ8_0
MiniCPM5 2B101tok/sQ8_039tok/sQ8_0
Spark X2.5 4B101tok/smlx-4bit39tok/smlx-4bit
Mellum2.1 12B A2.5B Thinking92tok/sQ8_035tok/sQ8_0
FrogNano 4B 260982tok/sQ8_032tok/sQ8_0
LFM2.5 2.6B81tok/sQ8_031tok/sQ8_0
LFM2.5 VL 3B81tok/sQ8_031tok/sQ8_0
Kimi VL A3B Thinking 250665tok/sQ8_025tok/sQ8_0
Kimi VL A3B63tok/smlx-8bit24tok/smlx-8bit
granite vision 4.1 4b62tok/sQ8_024tok/sQ8_0
granite 4.2 3b60tok/sQ8_023tok/sQ8_0
Ministral 3 3B Instruct 251252tok/sQ8_020tok/sQ8_0
GLM 4 9B 041451tok/smlx-5bit20tok/smlx-5bit
DeepSeek R1 Distill Qwen 7B47tok/sQ8_018tok/sQ8_0
LFM2.5 24B A2B45tok/sQ8_019tok/sQ5_K_M
GLM 4.6V Flash44tok/sQ8_017tok/sQ8_0
GLM 4.1V 9B Thinking38tok/smlx-8bit15tok/smlx-8bit
DeepSeek R1 Distill Llama 8B32tok/sQ8_013tok/sQ8_0
Ministral 3 8B Reasoning 251231tok/sQ8_012tok/sQ8_0
Muse Glimmer 30B23tok/sQ6_K10tok/sQ5_K_M
Ministral 3 14B Reasoning 251222tok/sQ8_010tok/sQ6_K
Qwen3.8 27B OBLITERATED22tok/smlx-4bitoffload
Devstral Small 250720tok/sQ5_K_Moffload
Magistral Small 250720tok/sQ5_K_Moffload
Magistral Small 250920tok/sQ5_K_Moffload
DeepSeek R1 Distill Qwen 14B19tok/sQ8_09tok/sQ5_K_M
Magistral Small 250619tok/sQ6_Koffload
Qwen 3.5 122B-A10Boffloadoffload
Qwen3 Coder Nextoffloadoffload
Nemotron 3 Super 120B-A12Boffloadwon't run
Mistral Small 4 119Boffloadoffload
GLM 4.5 Airoffloadwon't run
Qwen3 Next 80B-A3Boffloadoffload
Qwen3 32Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
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
gpt-oss 120Bwon'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 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 64k context the NVIDIA RTX PRO 4500 Blackwell runs 58 of the models we track fully in memory and the NVIDIA Tesla P40 48; only the NVIDIA RTX PRO 4500 Blackwell holds Gemma 4 31B.
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