readygpu

Intel Arc Pro B60 vs NVIDIA GeForce RTX 4070 Super

For running models locally, priced in Germany. At 128k context the first runs 26 models fully in memory, the second 12.

In short

The Intel Arc Pro B60 has more memory for models: 24 GB against 12 GB. At 128k context the Intel Arc Pro B60 runs 26 of the models we track fully in memory and the NVIDIA GeForce RTX 4070 Super 12; only the Intel Arc Pro B60 holds Gemma 4 26B-A4B. On the models both run fully in memory, the NVIDIA GeForce RTX 4070 Super is about 1.4× as fast as the Intel Arc Pro B60 (estimated, median across models). In Germany the Intel Arc Pro B60 costs 1.074 € at eBay and the NVIDIA GeForce RTX 4070 Super 950 € at Amazon: the NVIDIA GeForce RTX 4070 Super is 124 € cheaper.

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

Intel Arc Pro B60

1.074 €

eBay

Add to build
NVIDIA GeForce RTX 4070 Super

950 €

Amazon

Add to build

Specifications

SpecIntel Arc Pro B60NVIDIA GeForce RTX 4070 Super
GPUArc Pro B60GeForce RTX 4070 Super
Memory24 GB GDDR612 GB GDDR6X
Memory bus192-bit192-bit
Memory bandwidth456 GB/s504 GB/s
FP16 compute98.5 TFLOPS71 TFLOPS
SoftwareSYCL / oneAPICUDA
Board power200 W220 W
PCIe generationGen 5Gen 4
PCIe lanesx8x16

What each runs

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

ModelIntel Arc Pro B60NVIDIA GeForce RTX 4070 Super
Gemma 4 26B-A4B21tok/sQ5_K_Moffload
gpt-oss 20B22tok/sMXFP4offload
Gemma 4 12B15tok/sQ8_033tok/sQ4_K_M
Qwen 3.5 9B16tok/sQ8_031tok/sQ4_K_M
Qwen 3.5 4B26tok/sQ8_035tok/sQ8_0
Gemma 4 E4B19tok/sQ8_034tok/sQ5_K_M
LFM2.5 8B-A1B17tok/sQ8_0offload
Llama 3.1 8B10tok/sQ5_K_Moffload
Qwen2.5 0.5B107tok/sQ8_0146tok/sQ8_0
Qwen3.5 0.8B93tok/sQ8_0128tok/sQ8_0
Qwen3.5 2B74tok/sQ5_K_M102tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B40tok/sQ8_055tok/sQ8_0
Spark X2.5 4B29tok/smlx-4bit39tok/smlx-4bit
Mellum2.1 12B A2.5B Thinking27tok/sQ8_0offload
MiniCPM5 2B27tok/sQ8_038tok/sQ8_0
LFM2.5 2.6B21tok/sQ8_030tok/sQ6_K
LFM2.5 VL 3B21tok/sQ8_030tok/sQ6_K
Kimi VL A3B Thinking 250618tok/sQ8_0offload
Kimi VL A3B17tok/smlx-8bitoffload
GLM 4 9B 041417tok/smlx-5bitoffload
granite vision 4.1 4b16tok/sQ8_0offload
granite 4.2 3b16tok/sQ8_0offload
GLM 4.6V Flash15tok/sQ8_0offload
DeepSeek R1 Distill Qwen 7B15tok/sQ8_0offload
GLM 4.1V 9B Thinking13tok/smlx-8bitoffload
DeepSeek R1 Distill Llama 8B10tok/sQ5_K_Moffload
Qwen 3.8 27Boffloadoffload
Qwen 3.5 122B-A10Boffloadwon't run
Qwen 3.6 27Boffloadoffload
Gemma 4 31Boffloadoffload
Mistral Small 4 119Boffloadwon't run
Qwen 3.6 35B-A3Boffloadoffload
Qwen 3.5 27Boffloadoffload
Qwen 3.5 35B-A3Boffloadoffload
GLM 4.7 Flashoffloadoffload
Devstral Small 2 24Boffloadoffload
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 Coder 30B-A3Boffloadoffload
Gemma 3 27Boffloadoffload
Mistral Small 3.2 24Boffloadoffload
Ministral 3 14Boffloadoffload
Qwen3 14Boffloadoffload
DeepSeek R1 0528 Qwen3 8Boffloadoffload
Qwen3 8Boffloadoffload
Phi-4 14Boffloadoffload
Ministral 3 8Boffloadoffload
Granite 4.2 8Boffloadoffload
Ministral 3 8B Reasoning 2512offloadoffload
LFM2.5 24B A2Boffloadoffload
Qwen3.8 27B OBLITERATEDoffloadoffload
DeepSeek R1 Distill Qwen 14Boffloadoffload
Devstral Small 2507offloadoffload
Magistral Small 2506offloadoffload
Magistral Small 2507offloadoffload
Magistral Small 2509offloadoffload
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
Qwen3 Coder Nextwon't runwon't run
gpt-oss 120Bwon't runwon't run
GLM 4.5 Airwon't runwon't run
Qwen3 Next 80B-A3Bwon't runwon't run
Qwen3 32Bwon't runwon't run
DeepSeek R1 Distill Qwen 32Bwon'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 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 4.5Vwon'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 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
granite 4.2 30bwon't runwon't run

Questions

Which is better for local AI, the Intel Arc Pro B60 or the NVIDIA GeForce RTX 4070 Super?
Choose the Intel Arc Pro B60 to run bigger models. Choose the NVIDIA GeForce RTX 4070 Super for speed. Choose the NVIDIA GeForce RTX 4070 Super to spend less.
Which can run bigger models, the Intel Arc Pro B60 or the NVIDIA GeForce RTX 4070 Super?
At 128k context the Intel Arc Pro B60 runs 26 of the models we track fully in memory and the NVIDIA GeForce RTX 4070 Super 12; only the Intel Arc Pro B60 holds Gemma 4 26B-A4B.
Which is faster for local AI, the Intel Arc Pro B60 or the NVIDIA GeForce RTX 4070 Super?
On the models both run fully in memory, the NVIDIA GeForce RTX 4070 Super is about 1.4× as fast as the Intel Arc Pro B60 (estimated, median across models).
What is the price difference between the Intel Arc Pro B60 and the NVIDIA GeForce RTX 4070 Super?
In Germany the Intel Arc Pro B60 costs 1.074 € at eBay and the NVIDIA GeForce RTX 4070 Super 950 € at Amazon: the NVIDIA GeForce RTX 4070 Super is 124 € cheaper.

More comparisons

Intel Arc Pro B60 vs NVIDIA GeForce RTX 4070 Super for local AI (DE) · readygpu