readygpu

NVIDIA RTX PRO 4000 Blackwell vs NVIDIA RTX PRO 4500 Blackwell

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

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 RTX PRO 4000 Blackwell 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 1.3× as fast as the NVIDIA RTX PRO 4000 Blackwell (estimated, median across models).

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

NVIDIA RTX PRO 4000 Blackwell

Not priced here

Add to build
NVIDIA RTX PRO 4500 Blackwell

Not priced here

Add to build

Specifications

SpecNVIDIA RTX PRO 4000 BlackwellNVIDIA RTX PRO 4500 Blackwell
GPURTX PRO 4000 BlackwellRTX PRO 4500 Blackwell
Memory24 GB GDDR732 GB GDDR7
Memory bus192-bit256-bit
Memory bandwidth672 GB/s896 GB/s
FP16 compute46.9 TFLOPS54.94 TFLOPS
SoftwareCUDACUDA
Board power145 W200 W
PCIe generationGen 5Gen 5
PCIe lanesx16x16

What each runs

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

ModelNVIDIA RTX PRO 4000 BlackwellNVIDIA RTX PRO 4500 Blackwell
Qwen 3.8 27B19tok/sQ4_K_M20tok/sQ6_K
Qwen 3.6 27B17tok/sQ5_K_M21tok/sQ6_K
Gemma 4 31Boffload18tok/sQ6_K
Qwen 3.6 35B-A3B77tok/sQ4_K_M84tok/sQ6_K
Qwen 3.5 27B20tok/sQ4_K_M21tok/sQ6_K
Gemma 4 26B-A4B52tok/sUD-Q5_K_M58tok/sQ8_0
Qwen 3.5 35B-A3B77tok/sQ4_K_M87tok/sQ6_K
GLM 4.7 Flash38tok/sQ4_K_M44tok/sQ6_K
Devstral Small 2 24Boffload19tok/sQ6_K
Nemotron 3.5 Lightning 30B-A3B94tok/sMXFP4100tok/sUD-Q5_K_M
gpt-oss 20B62tok/sMXFP483tok/sMXFP4
Kimi Linear 48B-A3Boffload139tok/sQ4_K_M
Qwen3 Coder 30B-A3Boffload37tok/sQ6_K
Gemma 4 12B30tok/sQ8_040tok/sQ8_0
Qwen 3.5 9B36tok/sQ8_047tok/sQ8_0
Gemma 3 27B19tok/sQ4_K_M20tok/sQ6_K
Mistral Small 3.2 24Boffload19tok/sQ6_K
Ministral 3 14B19tok/sQ6_K22tok/sQ8_0
Qwen3 14B18tok/sQ6_K21tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B23tok/sQ8_030tok/sQ8_0
Qwen3 8B23tok/sQ8_030tok/sQ8_0
Phi-4 14B18tok/sQ5_K_M19tok/sQ8_0
Qwen 3.5 4B62tok/sQ8_083tok/sQ8_0
Ministral 3 8B23tok/sQ8_031tok/sQ8_0
Granite 4.2 8B21tok/sQ8_028tok/sQ8_0
Gemma 4 E4B41tok/sQ8_055tok/sQ8_0
LFM2.5 8B-A1B58tok/sQ8_078tok/sQ8_0
Llama 3.1 8B27tok/sQ6_K37tok/sQ6_K
Qwen2.5 0.5B312tok/sQ8_0416tok/sQ8_0
Qwen3.5 0.8B255tok/sQ8_0340tok/sQ8_0
Qwen3.5 2B184tok/sQ5_K_M246tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B110tok/sQ8_0147tok/sQ8_0
MiniCPM5 2B76tok/sQ8_0101tok/sQ8_0
Spark X2.5 4B76tok/smlx-4bit101tok/smlx-4bit
Mellum2.1 12B A2.5B Thinking69tok/sQ8_092tok/sQ8_0
FrogNano 4B 260961tok/sQ8_082tok/sQ8_0
LFM2.5 2.6B60tok/sQ8_081tok/sQ8_0
LFM2.5 VL 3B60tok/sQ8_081tok/sQ8_0
Kimi VL A3B Thinking 250649tok/sQ8_065tok/sQ8_0
Kimi VL A3B47tok/smlx-8bit63tok/smlx-8bit
granite vision 4.1 4b46tok/sQ8_062tok/sQ8_0
granite 4.2 3b45tok/sQ8_060tok/sQ8_0
Ministral 3 3B Instruct 251239tok/sQ8_052tok/sQ8_0
GLM 4 9B 041438tok/smlx-5bit51tok/smlx-5bit
LFM2.5 24B A2B36tok/sQ5_K_M45tok/sQ8_0
DeepSeek R1 Distill Qwen 7B35tok/sQ8_047tok/sQ8_0
GLM 4.6V Flash33tok/sQ8_044tok/sQ8_0
GLM 4.1V 9B Thinking29tok/smlx-8bit38tok/smlx-8bit
DeepSeek R1 Distill Llama 8B24tok/sQ8_032tok/sQ8_0
Ministral 3 8B Reasoning 251223tok/sQ8_031tok/sQ8_0
Muse Glimmer 30B20tok/sQ5_K_M23tok/sQ6_K
Ministral 3 14B Reasoning 251219tok/sQ6_K22tok/sQ8_0
DeepSeek R1 Distill Qwen 14B18tok/sQ5_K_M19tok/sQ8_0
Devstral Small 2507offload20tok/sQ5_K_M
Magistral Small 2506offload19tok/sQ6_K
Magistral Small 2507offload20tok/sQ5_K_M
Magistral Small 2509offload20tok/sQ5_K_M
Qwen3.8 27B OBLITERATEDoffload22tok/smlx-4bit
Qwen 3.5 122B-A10Boffloadoffload
Qwen3 Coder Nextoffloadoffload
Nemotron 3 Super 120B-A12Bwon't runoffload
Mistral Small 4 119Boffloadoffload
GLM 4.5 Airwon't runoffload
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 4000 Blackwell or the NVIDIA RTX PRO 4500 Blackwell?
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 4000 Blackwell or the NVIDIA RTX PRO 4500 Blackwell?
At 64k context the NVIDIA RTX PRO 4500 Blackwell runs 58 of the models we track fully in memory and the NVIDIA RTX PRO 4000 Blackwell 48; only the NVIDIA RTX PRO 4500 Blackwell holds Gemma 4 31B.
Which is faster for local AI, the NVIDIA RTX PRO 4000 Blackwell or the NVIDIA RTX PRO 4500 Blackwell?
On the models both run fully in memory, the NVIDIA RTX PRO 4500 Blackwell is about 1.3× as fast as the NVIDIA RTX PRO 4000 Blackwell (estimated, median across models).

More comparisons

More hardware for local AI