readygpu

Intel Arc Pro B60 vs NVIDIA GeForce RTX 4070 Ti Super

For running models locally, priced in the US. At 8k context the first runs 51 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 8k context the Intel Arc Pro B60 runs 51 of the models we track fully in memory and the NVIDIA GeForce RTX 4070 Ti Super 37; only the Intel Arc Pro B60 holds Qwen 3.8 27B. On the models both run fully in memory, the NVIDIA GeForce RTX 4070 Ti Super is about 1.8× as fast as the Intel Arc Pro B60 (estimated, median across models). In the US the Intel Arc Pro B60 costs $650 at Amazon and the NVIDIA GeForce RTX 4070 Ti Super $984 at Amazon: the Intel Arc Pro B60 is $334 cheaper.

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

Intel Arc Pro B60

$650

Amazon

Add to build
NVIDIA GeForce RTX 4070 Ti Super

$984

Amazon

Add to build

Specifications

SpecIntel Arc Pro B60NVIDIA GeForce RTX 4070 Ti Super
GPUArc Pro B60GeForce RTX 4070 Ti Super
Memory24 GB GDDR616 GB GDDR6X
Memory bus192-bit256-bit
Memory bandwidth456 GB/s672 GB/s
FP16 compute98.5 TFLOPS88 TFLOPS
SoftwareSYCL / oneAPICUDA
Board power200 W285 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 Ti Super
Qwen 3.8 27B10tok/sUD-Q6_Koffload
Qwen 3.6 27B10tok/sQ6_Koffload
Gemma 4 31B10tok/sQ5_K_Moffload
Qwen 3.6 35B-A3B60tok/sQ4_K_Moffload
Qwen 3.5 27B10tok/sQ6_Koffload
Gemma 4 26B-A4B32tok/sUD-Q6_Koffload
Qwen 3.5 35B-A3B61tok/sQ4_K_Moffload
GLM 4.7 Flash31tok/sQ5_K_Moffload
Devstral Small 2 24B11tok/sQ6_K27tok/sQ4_K_M
gpt-oss 20B48tok/sMXFP495tok/sMXFP4
Qwen3 Coder 30B-A3B43tok/sQ5_K_Moffload
Qwen3 32B10tok/sQ4_K_Moffload
Gemma 4 12B17tok/sQ8_032tok/sQ8_0
Qwen 3.5 9B23tok/sQ8_042tok/sQ8_0
Mistral Small 3.2 24B11tok/sQ6_K27tok/sQ4_K_M
DeepSeek R1 Distill Qwen 32B10tok/sQ4_K_Moffload
Gemma 3 27B10tok/sQ6_Koffload
Ministral 3 14B15tok/sQ8_027tok/sQ8_0
Qwen3 14B13tok/sQ8_031tok/sQ6_K
DeepSeek R1 0528 Qwen3 8B23tok/sQ8_042tok/sQ8_0
Qwen3 8B23tok/sQ8_042tok/sQ8_0
Phi-4 14B13tok/sQ8_030tok/sQ6_K
Qwen 3.5 4B48tok/sQ8_087tok/sQ8_0
Ministral 3 8B22tok/sQ8_041tok/sQ8_0
Granite 4.2 8B21tok/sQ8_039tok/sQ8_0
Gemma 4 E4B27tok/sQ8_049tok/sQ8_0
LFM2.5 8B-A1B86tok/sQ8_0170tok/sQ8_0
Llama 3.1 8B30tok/sQ6_K54tok/sQ6_K
Qwen2.5 0.5B361tok/sQ8_0660tok/sQ8_0
Qwen3.5 0.8B245tok/sQ8_0447tok/sQ8_0
Qwen3.5 2B147tok/sQ5_K_M268tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B107tok/sQ8_0196tok/sQ8_0
MiniCPM5 2B75tok/sQ8_0137tok/sQ8_0
LFM2.5 2.6B68tok/sQ8_0123tok/sQ8_0
LFM2.5 VL 3B68tok/sQ8_0123tok/sQ8_0
granite vision 4.1 4b53tok/sQ8_097tok/sQ8_0
LFM2.5 24B A2B52tok/sQ6_Koffload
granite 4.2 3b50tok/sQ8_091tok/sQ8_0
Mellum2.1 12B A2.5B Thinking45tok/sQ8_089tok/sQ8_0
Kimi VL A3B36tok/smlx-8bit90tok/smlx-6bit
DeepSeek R1 Distill Qwen 7B27tok/sQ8_049tok/sQ8_0
DeepSeek R1 Distill Llama 8B24tok/sQ8_043tok/sQ8_0
Ministral 3 8B Reasoning 251222tok/sQ8_041tok/sQ8_0
GLM 4.6V Flash22tok/sQ8_040tok/sQ8_0
GLM 4.1V 9B Thinking19tok/smlx-8bit34tok/smlx-8bit
DeepSeek R1 Distill Qwen 14B13tok/sQ8_030tok/sQ6_K
Devstral Small 250713tok/sQ5_K_M27tok/sQ4_K_M
Magistral Small 250713tok/sQ5_K_M27tok/sQ4_K_M
Magistral Small 250913tok/sQ5_K_M27tok/sQ4_K_M
Magistral Small 250611tok/sQ6_K27tok/sQ4_K_M
granite 4.2 30b10tok/sQ5_K_Moffload
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
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
Kimi Linear 48B-A3Boffloadoffload
Llama 3.3 70Boffloadwon't run
DeepSeek R1 Distill Llama 70Boffloadwon't run
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
DeepSeek R1won't runwon't run
DeepSeek R1 0528won't runwon't run
DeepSeek V3 0324won't runwon't run
DeepSeek V3.1won'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 4.6Vwon'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 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 GeForce RTX 4070 Ti Super?
Choose the Intel Arc Pro B60 to run bigger models. Choose the NVIDIA GeForce RTX 4070 Ti Super for speed. Choose the Intel Arc Pro B60 to spend less.
Which can run bigger models, the Intel Arc Pro B60 or the NVIDIA GeForce RTX 4070 Ti Super?
At 8k context the Intel Arc Pro B60 runs 51 of the models we track fully in memory and the NVIDIA GeForce RTX 4070 Ti Super 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 GeForce RTX 4070 Ti Super?
On the models both run fully in memory, the NVIDIA GeForce RTX 4070 Ti Super is about 1.8× 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 Ti Super?
In the US the Intel Arc Pro B60 costs $650 at Amazon and the NVIDIA GeForce RTX 4070 Ti Super $984 at Amazon: the Intel Arc Pro B60 is $334 cheaper.

More comparisons