Intel Arc Pro B60 vs NVIDIA RTX PRO 4000 Blackwell
For running models locally, priced in Germany. At 32k context the first runs 57 models fully in memory, the second 57.
In short
Both have 24 GB of memory for models; the Intel Arc Pro B60 has 456 GB/s of bandwidth and the NVIDIA RTX PRO 4000 Blackwell 672 GB/s. At 32k context both run the same 57 models we track fully in memory. On the models both run fully in memory, the NVIDIA RTX PRO 4000 Blackwell is about 1.8× as fast as the Intel Arc Pro B60 (estimated, median across models).
Updated . Speeds are estimates; how they are worked out.
Specifications
| Spec | Intel Arc Pro B60 | NVIDIA RTX PRO 4000 Blackwell |
|---|---|---|
| GPU | Arc Pro B60 | RTX PRO 4000 Blackwell |
| Memory | 24 GB GDDR6 | 24 GB GDDR7 |
| Memory bus | 192-bit | 192-bit |
| Memory bandwidth | 456 GB/s | 672 GB/s |
| FP16 compute | 98.5 TFLOPS | 46.9 TFLOPS |
| Software | SYCL / oneAPI | CUDA |
| Board power | 200 W | 145 W |
| PCIe generation | Gen 5 | Gen 5 |
| PCIe lanes | x8 | x16 |
What each runs
Estimated decode speed with the most precise quant that fits each one est.
| Model | Intel Arc Pro B60 | NVIDIA RTX PRO 4000 Blackwell |
|---|---|---|
| Qwen 3.8 27B | 10tok/sQ5_K_M | 18tok/sQ5_K_M |
| Qwen 3.6 27B | 11tok/sQ5_K_M | 19tok/sQ5_K_M |
| Gemma 4 31B | 10tok/sQ4_K_M | 19tok/sQ4_K_M |
| Qwen 3.6 35B-A3B | 48tok/sQ4_K_M | 96tok/sQ4_K_M |
| Qwen 3.5 27B | 10tok/sQ5_K_M | 19tok/sQ5_K_M |
| Gemma 4 26B-A4B | 28tok/sQ6_K | 56tok/sUD-Q6_K |
| Qwen 3.5 35B-A3B | 49tok/sQ4_K_M | 97tok/sQ4_K_M |
| GLM 4.7 Flash | 24tok/sQ5_K_M | 47tok/sQ5_K_M |
| Devstral Small 2 24B | 10tok/sQ5_K_M | 19tok/sQ5_K_M |
| Nemotron 3.5 Lightning 30B-A3B | 51tok/sMXFP4 | 102tok/sMXFP4 |
| gpt-oss 20B | 39tok/sMXFP4 | 77tok/sMXFP4 |
| Qwen3 Coder 30B-A3B | 25tok/sQ4_K_M | 50tok/sQ4_K_M |
| Gemma 4 12B | 17tok/sQ8_0 | 31tok/sQ8_0 |
| Qwen 3.5 9B | 21tok/sQ8_0 | 39tok/sQ8_0 |
| Mistral Small 3.2 24B | 10tok/sQ5_K_M | 19tok/sQ5_K_M |
| Gemma 3 27B | 10tok/sQ5_K_M | 19tok/sQ5_K_M |
| Ministral 3 14B | 12tok/sQ8_0 | 21tok/sQ8_0 |
| Qwen3 14B | 11tok/sQ8_0 | 20tok/sQ8_0 |
| DeepSeek R1 0528 Qwen3 8B | 17tok/sQ8_0 | 31tok/sQ8_0 |
| Qwen3 8B | 17tok/sQ8_0 | 31tok/sQ8_0 |
| Phi-4 14B | 10tok/sQ8_0 | 19tok/sQ8_0 |
| Qwen 3.5 4B | 41tok/sQ8_0 | 74tok/sQ8_0 |
| Ministral 3 8B | 17tok/sQ8_0 | 31tok/sQ8_0 |
| Granite 4.2 8B | 16tok/sQ8_0 | 28tok/sQ8_0 |
| Gemma 4 E4B | 25tok/sQ8_0 | 45tok/sQ8_0 |
| LFM2.5 8B-A1B | 47tok/sQ8_0 | 94tok/sQ8_0 |
| Llama 3.1 8B | 21tok/sQ6_K | 38tok/sQ6_K |
| Qwen2.5 0.5B | 244tok/sQ8_0 | 446tok/sQ8_0 |
| Qwen3.5 0.8B | 185tok/sQ8_0 | 338tok/sQ8_0 |
| Qwen3.5 2B | 123tok/sQ5_K_M | 224tok/sQ5_K_M |
| DeepSeek R1 Distill Qwen 1.5B | 81tok/sQ8_0 | 147tok/sQ8_0 |
| MiniCPM5 2B | 56tok/sQ8_0 | 102tok/sQ8_0 |
| Spark X2.5 4B | 53tok/smlx-4bit | 97tok/smlx-4bit |
| LFM2.5 2.6B | 47tok/sQ8_0 | 85tok/sQ8_0 |
| LFM2.5 VL 3B | 47tok/sQ8_0 | 85tok/sQ8_0 |
| FrogNano 4B 2609 | 40tok/sQ8_0 | 73tok/sQ8_0 |
| Mellum2.1 12B A2.5B Thinking | 40tok/sQ8_0 | 79tok/sQ8_0 |
| granite vision 4.1 4b | 36tok/sQ8_0 | 66tok/sQ8_0 |
| granite 4.2 3b | 35tok/sQ8_0 | 63tok/sQ8_0 |
| Ministral 3 3B Instruct 2512 | 32tok/sQ8_0 | 58tok/sQ8_0 |
| Kimi VL A3B Thinking 2506 | 30tok/sQ8_0 | 61tok/sQ8_0 |
| Kimi VL A3B | 29tok/smlx-8bit | 58tok/smlx-8bit |
| LFM2.5 24B A2B | 28tok/sQ6_K | 56tok/sQ6_K |
| GLM 4 9B 0414 | 24tok/smlx-5bit | 43tok/smlx-5bit |
| DeepSeek R1 Distill Qwen 7B | 23tok/sQ8_0 | 42tok/sQ8_0 |
| GLM 4.6V Flash | 20tok/sQ8_0 | 37tok/sQ8_0 |
| DeepSeek R1 Distill Llama 8B | 18tok/sQ8_0 | 33tok/sQ8_0 |
| GLM 4.1V 9B Thinking | 17tok/smlx-8bit | 32tok/smlx-8bit |
| Ministral 3 8B Reasoning 2512 | 17tok/sQ8_0 | 31tok/sQ8_0 |
| Ministral 3 14B Reasoning 2512 | 12tok/sQ8_0 | 21tok/sQ8_0 |
| Muse Glimmer 30B | 11tok/sQ5_K_M | 17tok/sQ6_K |
| DeepSeek R1 Distill Qwen 14B | 10tok/sQ8_0 | 19tok/sQ8_0 |
| Devstral Small 2507 | 10tok/sQ5_K_M | 19tok/sQ5_K_M |
| Magistral Small 2506 | 10tok/sQ5_K_M | 19tok/sQ5_K_M |
| Magistral Small 2507 | 10tok/sQ5_K_M | 19tok/sQ5_K_M |
| Magistral Small 2509 | 10tok/sQ5_K_M | 19tok/sQ5_K_M |
| Qwen3.8 27B OBLITERATED | 10tok/smlx-4bit | 18tok/smlx-4bit |
| Qwen 3.5 122B-A10B | offload | offload |
| Qwen3 Coder Next | offload | offload |
| Mistral Small 4 119B | offload | offload |
| GLM 4.5 Air | offload | offload |
| Qwen3 Next 80B-A3B | offload | offload |
| Kimi Linear 48B-A3B | offload | offload |
| Qwen3 32B | offload | offload |
| DeepSeek R1 Distill Qwen 32B | offload | offload |
| granite 4.2 30b | offload | offload |
| DeepSeek V4 Flash | won't run | won't run |
| GLM 5.3 Flash | won't run | won't run |
| Qwen 3.8 Flash Next | won't run | won't run |
| MiniMax M2.7 | won't run | won't run |
| Nemotron 3 Super 120B-A12B | won't run | won't run |
| gpt-oss 120B | won't run | won't run |
| Llama 3.3 70B | won't run | won't run |
| DeepSeek R1 | won't run | won't run |
| DeepSeek R1 0528 | won't run | won't run |
| DeepSeek R1 Distill Llama 70B | won't run | won't run |
| DeepSeek R1 Zero | won't run | won't run |
| DeepSeek V3 | won't run | won't run |
| DeepSeek V3 0324 | won't run | won't run |
| DeepSeek V3.1 | won't run | won't run |
| DeepSeek V3.1 Terminus | won't run | won't run |
| DeepSeek V3.2 | won't run | won't run |
| DeepSeek V4 Flash 0731 | won't run | won't run |
| DeepSeek V4 Flash Vision Exp | won't run | won't run |
| Devstral 2 123B Instruct 2512 | won't run | won't run |
| GLM 4.5 | won't run | won't run |
| GLM 4.5V | won't run | won't run |
| GLM 4.6 | won't run | won't run |
| GLM 4.6V | won't run | won't run |
| GLM 4.7 | won't run | won't run |
| GLM 5 | won't run | won't run |
| GLM 5.1 | won't run | won't run |
| GLM 5.2 | won't run | won't run |
| GLM 5.3 | won't run | won't run |
| Kimi Dev 72B | won't run | won't run |
| Kimi K2 | won't run | won't run |
| Kimi K2 Instruct 0905 | won't run | won't run |
| Kimi K2 Thinking | won't run | won't run |
| Kimi K2.5 | won't run | won't run |
| MiniMax M2 | won't run | won't run |
| MiniMax M2.1 | won't run | won't run |
| MiniMax M2.5 | won't run | won't run |
| MiniMax M3 | won't run | won't run |
| Mistral Medium 3.5 128B | won't run | won't run |
Questions
- Which is better for local AI, the Intel Arc Pro B60 or the NVIDIA RTX PRO 4000 Blackwell?
- Choose the NVIDIA RTX PRO 4000 Blackwell for speed.
- Which can run bigger models, the Intel Arc Pro B60 or the NVIDIA RTX PRO 4000 Blackwell?
- At 32k context both run the same 57 models we track fully in memory.
- Which is faster for local AI, the Intel Arc Pro B60 or the NVIDIA RTX PRO 4000 Blackwell?
- On the models both run fully in memory, the NVIDIA RTX PRO 4000 Blackwell is about 1.8× as fast as the Intel Arc Pro B60 (estimated, median across models).
More comparisons
- Intel Arc A770 16GB vs Intel Arc Pro B60
- Intel Arc Pro B60 vs Intel Arc Pro B70
- Intel Arc Pro B60 vs Mac mini M4 16GB
- Intel Arc Pro B60 vs NVIDIA GeForce RTX 4070 Super
- Intel Arc Pro B60 vs AMD Radeon RX 7800 XT
- Intel Arc Pro B60 vs AMD Radeon RX 7900 XT
- Intel Arc Pro B60 vs NVIDIA Tesla P40
- Intel Arc Pro B70 vs NVIDIA RTX PRO 4000 Blackwell
- AMD Radeon AI PRO R9700 vs NVIDIA RTX PRO 4000 Blackwell
- NVIDIA GeForce RTX 3090 vs NVIDIA RTX PRO 4000 Blackwell