readygpu

Intel Arc Pro B60 vs NVIDIA GeForce RTX 5070

For running models locally, priced in the US. At 64k context the first runs 40 models fully in memory, the second 16.

In short

The Intel Arc Pro B60 has more memory for models: 24 GB against 12 GB. At 64k context the Intel Arc Pro B60 runs 40 of the models we track fully in memory and the NVIDIA GeForce RTX 5070 16; only the Intel Arc Pro B60 holds Qwen 3.8 27B. On the models both run fully in memory, the NVIDIA GeForce RTX 5070 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 5070 $750 at eBay: the Intel Arc Pro B60 is $100 cheaper.

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

Intel Arc Pro B60

$650

Amazon

Add to build
NVIDIA GeForce RTX 5070

$750

eBay

Add to build

Specifications

SpecIntel Arc Pro B60NVIDIA GeForce RTX 5070
GPUArc Pro B60GeForce RTX 5070
Memory24 GB GDDR612 GB GDDR7
Memory bus192-bit192-bit
Memory bandwidth456 GB/s672 GB/s
FP16 compute98.5 TFLOPS62 TFLOPS
SoftwareSYCL / oneAPICUDA
Board power200 W250 W
PCIe generationGen 5Gen 5
PCIe lanesx8x16

What each runs

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

ModelIntel Arc Pro B60NVIDIA GeForce RTX 5070
Qwen 3.8 27B10tok/sQ4_K_Moffload
Qwen 3.6 27B11tok/sQ4_K_Moffload
Qwen 3.6 35B-A3B39tok/sUD-Q4_K_Moffload
Qwen 3.5 27B11tok/sQ4_K_Moffload
Gemma 4 26B-A4B26tok/sUD-Q5_K_Moffload
Qwen 3.5 35B-A3B39tok/sQ4_K_Moffload
GLM 4.7 Flash19tok/sQ4_K_Moffload
gpt-oss 20B31tok/sMXFP4offload
Gemma 4 12B16tok/sQ8_042tok/sQ5_K_M
Qwen 3.5 9B19tok/sQ8_043tok/sQ6_K
Gemma 3 27B10tok/sQ4_K_Moffload
Ministral 3 14B10tok/sQ6_Koffload
Qwen3 14B10tok/sQ6_Koffload
DeepSeek R1 0528 Qwen3 8B12tok/sQ8_0offload
Qwen3 8B12tok/sQ8_0offload
Phi-4 14B10tok/sQ4_K_Moffload
Qwen 3.5 4B34tok/sQ8_062tok/sQ8_0
Ministral 3 8B13tok/sQ8_0offload
Granite 4.2 8B11tok/sQ8_0offload
Gemma 4 E4B23tok/sQ8_041tok/sQ8_0
LFM2.5 8B-A1B29tok/sQ8_062tok/sUD-Q6_K
Llama 3.1 8B15tok/sQ6_Koffload
Qwen2.5 0.5B171tok/sQ8_0312tok/sQ8_0
Qwen3.5 0.8B139tok/sQ8_0255tok/sQ8_0
Qwen3.5 2B101tok/sQ5_K_M184tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B60tok/sQ8_0110tok/sQ8_0
MiniCPM5 2B42tok/sQ8_076tok/sQ8_0
Mellum2.1 12B A2.5B Thinking34tok/sQ8_0offload
LFM2.5 2.6B33tok/sQ8_060tok/sQ8_0
LFM2.5 VL 3B33tok/sQ8_060tok/sQ8_0
granite vision 4.1 4b25tok/sQ8_046tok/sQ8_0
granite 4.2 3b25tok/sQ8_045tok/sQ8_0
Kimi VL A3B24tok/smlx-8bitoffload
DeepSeek R1 Distill Qwen 7B19tok/sQ8_042tok/sQ6_K
LFM2.5 24B A2B19tok/sQ4_K_Moffload
GLM 4.6V Flash18tok/sQ8_047tok/sQ4_K_M
GLM 4.1V 9B Thinking16tok/smlx-8bitoffload
DeepSeek R1 Distill Llama 8B13tok/sQ8_0offload
Ministral 3 8B Reasoning 251213tok/sQ8_0offload
DeepSeek R1 Distill Qwen 14B10tok/sQ5_K_Moffload
Qwen 3.5 122B-A10Boffloadwon't run
Qwen3 Coder Nextoffloadwon't run
Gemma 4 31Boffloadoffload
Mistral Small 4 119Boffloadwon't run
Qwen3 Next 80B-A3Boffloadwon't run
Devstral Small 2 24Boffloadoffload
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 Coder 30B-A3Boffloadoffload
Qwen3 32Boffloadoffload
Mistral Small 3.2 24Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
Devstral Small 2507offloadoffload
Magistral Small 2506offloadoffload
Magistral Small 2507offloadoffload
Magistral Small 2509offloadoffload
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
GLM 4.5 Airwon'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 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 5070?
Choose the Intel Arc Pro B60 to run bigger models. Choose the NVIDIA GeForce RTX 5070 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 5070?
At 64k context the Intel Arc Pro B60 runs 40 of the models we track fully in memory and the NVIDIA GeForce RTX 5070 16; 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 5070?
On the models both run fully in memory, the NVIDIA GeForce RTX 5070 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 5070?
In the US the Intel Arc Pro B60 costs $650 at Amazon and the NVIDIA GeForce RTX 5070 $750 at eBay: the Intel Arc Pro B60 is $100 cheaper.

More comparisons