readygpu

Intel Arc Pro B60 vs NVIDIA RTX PRO 2000 Blackwell

For running models locally, priced in Germany. At 32k context the first runs 58 models fully in memory, the second 37.

In short

The Intel Arc Pro B60 has more memory for models: 24 GB against 16 GB. At 32k context the Intel Arc Pro B60 runs 58 of the models we track fully in memory and the NVIDIA RTX PRO 2000 Blackwell 37; only the Intel Arc Pro B60 holds Qwen 3.8 27B. On the models both run fully in memory, the Intel Arc Pro B60 is about 1.3× as fast as the NVIDIA RTX PRO 2000 Blackwell (estimated, median across models). In Germany the Intel Arc Pro B60 costs 1.074 € at eBay and the NVIDIA RTX PRO 2000 Blackwell 1.000 € at Amazon: the NVIDIA RTX PRO 2000 Blackwell is 74 € cheaper.

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

Intel Arc Pro B60

1.074 €

eBay

Add to build
NVIDIA RTX PRO 2000 Blackwell

1.000 €

Amazon

Add to build

Specifications

SpecIntel Arc Pro B60NVIDIA RTX PRO 2000 Blackwell
GPUArc Pro B60RTX PRO 2000 Blackwell
Memory24 GB GDDR616 GB GDDR7
Memory bus192-bit128-bit
Memory bandwidth456 GB/s288 GB/s
FP16 compute98.5 TFLOPS17.03 TFLOPS
SoftwareSYCL / oneAPICUDA
Board power200 W70 W
PCIe generationGen 5Gen 5
PCIe lanesx8x8

What each runs

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

ModelIntel Arc Pro B60NVIDIA RTX PRO 2000 Blackwell
Qwen 3.8 27B10tok/sQ5_K_Moffload
Qwen 3.6 27B11tok/sQ5_K_Moffload
Gemma 4 31B10tok/sQ4_K_Moffload
Qwen 3.6 35B-A3B48tok/sQ4_K_Moffload
Qwen 3.5 27B10tok/sQ5_K_Moffload
Gemma 4 26B-A4B28tok/sQ6_Koffload
Qwen 3.5 35B-A3B49tok/sQ4_K_Moffload
GLM 4.7 Flash24tok/sQ5_K_Moffload
Devstral Small 2 24B10tok/sQ5_K_Moffload
Nemotron 3.5 Lightning 30B-A3B51tok/sMXFP4offload
gpt-oss 20B39tok/sMXFP433tok/sMXFP4
Qwen3 Coder 30B-A3B25tok/sQ4_K_Moffload
Gemma 4 12B17tok/sQ8_013tok/sQ8_0
Qwen 3.5 9B21tok/sQ8_017tok/sQ8_0
Mistral Small 3.2 24B10tok/sQ5_K_Moffload
Gemma 3 27B10tok/sQ5_K_Moffload
Ministral 3 14B12tok/sQ8_012tok/sQ5_K_M
Qwen3 14B11tok/sQ8_012tok/sQ4_K_M
DeepSeek R1 0528 Qwen3 8B17tok/sQ8_013tok/sQ8_0
Qwen3 8B17tok/sQ8_013tok/sQ8_0
Phi-4 14B10tok/sQ8_0offload
Qwen 3.5 4B41tok/sQ8_032tok/sQ8_0
Ministral 3 8B17tok/sQ8_013tok/sQ8_0
Granite 4.2 8B16tok/sQ8_012tok/sQ8_0
Gemma 4 E4B25tok/sQ8_020tok/sQ8_0
LFM2.5 8B-A1B47tok/sQ8_040tok/sQ8_0
Llama 3.1 8B21tok/sQ6_K16tok/sQ6_K
Qwen2.5 0.5B244tok/sQ8_0191tok/sQ8_0
Qwen3.5 0.8B185tok/sQ8_0145tok/sQ8_0
Qwen3.5 2B123tok/sQ5_K_M96tok/sQ5_K_M
LFM3 1.7B101tok/sQ8_079tok/sQ8_0
DeepSeek R1 Distill Qwen 1.5B81tok/sQ8_063tok/sQ8_0
MiniCPM5 2B56tok/sQ8_044tok/sQ8_0
Spark X2.5 4B53tok/smlx-4bit42tok/smlx-4bit
LFM2.5 2.6B47tok/sQ8_037tok/sQ8_0
LFM2.5 VL 3B47tok/sQ8_037tok/sQ8_0
FrogNano 4B 260940tok/sQ8_031tok/sQ8_0
Mellum2.1 12B A2.5B Thinking40tok/sQ8_034tok/sQ8_0
granite vision 4.1 4b36tok/sQ8_028tok/sQ8_0
granite 4.2 3b35tok/sQ8_027tok/sQ8_0
Ministral 3 3B Instruct 251232tok/sQ8_025tok/sQ8_0
Kimi VL A3B Thinking 250630tok/sQ8_036tok/sQ4_K_M
Kimi VL A3B29tok/smlx-8bit30tok/smlx-6bit
LFM2.5 24B A2B28tok/sQ6_Koffload
GLM 4 9B 041424tok/smlx-5bit19tok/smlx-5bit
DeepSeek R1 Distill Qwen 7B23tok/sQ8_018tok/sQ8_0
GLM 4.6V Flash20tok/sQ8_016tok/sQ8_0
DeepSeek R1 Distill Llama 8B18tok/sQ8_014tok/sQ8_0
GLM 4.1V 9B Thinking17tok/smlx-8bit14tok/smlx-8bit
Ministral 3 8B Reasoning 251217tok/sQ8_013tok/sQ8_0
Ministral 3 14B Reasoning 251212tok/sQ8_012tok/sQ5_K_M
Muse Glimmer 30B11tok/sQ5_K_Moffload
DeepSeek R1 Distill Qwen 14B10tok/sQ8_012tok/sQ4_K_M
Devstral Small 250710tok/sQ5_K_Moffload
Magistral Small 250610tok/sQ5_K_Moffload
Magistral Small 250710tok/sQ5_K_Moffload
Magistral Small 250910tok/sQ5_K_Moffload
Qwen3.8 27B OBLITERATED10tok/smlx-4bitoffload
Qwen 3.5 122B-A10Boffloadoffload
Qwen3 Coder Nextoffloadwon't run
Mistral Small 4 119Boffloadoffload
GLM 4.5 Airoffloadwon't run
Qwen3 Next 80B-A3Boffloadwon't run
Kimi Linear 48B-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
Nemotron 3 Super 120B-A12Bwon'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 Intel Arc Pro B60 or the NVIDIA RTX PRO 2000 Blackwell?
Choose the Intel Arc Pro B60 to run bigger models. Choose the Intel Arc Pro B60 for speed. Choose the NVIDIA RTX PRO 2000 Blackwell to spend less.
Which can run bigger models, the Intel Arc Pro B60 or the NVIDIA RTX PRO 2000 Blackwell?
At 32k context the Intel Arc Pro B60 runs 58 of the models we track fully in memory and the NVIDIA RTX PRO 2000 Blackwell 37; only the Intel Arc Pro B60 holds Qwen 3.8 27B.
Which is faster for local AI, the Intel Arc Pro B60 or the NVIDIA RTX PRO 2000 Blackwell?
On the models both run fully in memory, the Intel Arc Pro B60 is about 1.3× as fast as the NVIDIA RTX PRO 2000 Blackwell (estimated, median across models).
What is the price difference between the Intel Arc Pro B60 and the NVIDIA RTX PRO 2000 Blackwell?
In Germany the Intel Arc Pro B60 costs 1.074 € at eBay and the NVIDIA RTX PRO 2000 Blackwell 1.000 € at Amazon: the NVIDIA RTX PRO 2000 Blackwell is 74 € cheaper.

More comparisons

More hardware for local AI