readygpu

Intel Arc Pro B60 vs AMD Radeon AI PRO R9700

For running models locally, priced in India. At 32k context the first runs 26 models fully in memory, the second 29.

In short

The AMD Radeon AI PRO R9700 has more memory for models: 32 GB against 24 GB. At 32k context the AMD Radeon AI PRO R9700 runs 29 of the models we track fully in memory and the Intel Arc Pro B60 26; only the AMD Radeon AI PRO R9700 holds Kimi Linear 48B-A3B. On the models both run fully in memory, the AMD Radeon AI PRO R9700 is about 1.5× as fast as the Intel Arc Pro B60 (estimated, median across models).

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

Intel Arc Pro B60

Not priced here

Add to build
AMD Radeon AI PRO R9700

Not priced here

Add to build

Specifications

SpecIntel Arc Pro B60AMD Radeon AI PRO R9700
GPUArc Pro B60Radeon AI PRO R9700
Memory24 GB GDDR632 GB GDDR6
Memory bus192-bit256-bit
Memory bandwidth456 GB/s640 GB/s
FP16 compute98.5 TFLOPS191 TFLOPS
SoftwareSYCL / oneAPIROCm
Board power200 W300 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 B60AMD Radeon AI PRO R9700
Qwen 3.8 27B10tok/sUD-Q5_K_M11tok/sQ8_0
Qwen 3.6 27B11tok/sQ5_K_M11tok/sQ8_0
Gemma 4 31B10tok/sQ4_K_M12tok/sQ6_K
Qwen 3.6 35B-A3B49tok/sUD-Q4_K_M66tok/sUD-Q6_K
Qwen 3.5 27B10tok/sQ5_K_M11tok/sQ8_0
Gemma 4 26B-A4B30tok/sUD-Q5_K_M42tok/sQ8_0
Qwen 3.5 35B-A3B49tok/sQ4_K_M67tok/sQ6_K
GLM 4.7 Flash24tok/sQ5_K_M36tok/sQ6_K
Devstral Small 2 24B10tok/sQ5_K_M12tok/sQ8_0
gpt-oss 20B39tok/sMXFP465tok/sMXFP4
Qwen3 Coder 30B-A3B25tok/sQ4_K_M37tok/sQ6_K
Kimi Linear 48B-A3Boffload99tok/sQ4_K_M
Qwen3 32Boffload11tok/sQ5_K_M
Gemma 4 12B17tok/sQ8_026tok/sQ8_0
Qwen 3.5 9B21tok/sQ8_033tok/sQ8_0
Mistral Small 3.2 24B10tok/sQ5_K_M12tok/sQ8_0
Gemma 3 27B10tok/sQ5_K_M11tok/sQ8_0
DeepSeek R1 Distill Qwen 32Boffload11tok/sQ5_K_M
Ministral 3 14B12tok/sQ8_018tok/sQ8_0
Qwen3 14B11tok/sQ8_017tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B17tok/sQ8_026tok/sQ8_0
Qwen3 8B17tok/sQ8_026tok/sQ8_0
Phi-4 14B10tok/sQ8_016tok/sQ8_0
Qwen 3.5 4B41tok/sQ8_063tok/sQ8_0
Ministral 3 8B17tok/sQ8_026tok/sQ8_0
Granite 4.2 8B16tok/sQ8_024tok/sQ8_0
Gemma 4 E4B25tok/sQ8_038tok/sQ8_0
LFM2.5 8B-A1B47tok/sQ8_079tok/sQ8_0
Llama 3.1 8B21tok/sQ6_K32tok/sQ6_K
Qwen 3.5 122B-A10Boffloadoffload
Qwen3 Coder Nextoffloadoffload
Nemotron 3 Super 120B-A12Bwon't runoffload
Mistral Small 4 119Boffloadoffload
GLM 4.5 Airoffloadoffload
Qwen3 Next 80B-A3Boffloadoffload
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
Llama 3.3 70Bwon't runoffload
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
gpt-oss 120Bwon't runwon't run

Questions

Which is better for local AI, the Intel Arc Pro B60 or the AMD Radeon AI PRO R9700?
Choose the AMD Radeon AI PRO R9700 to run bigger models. Choose the AMD Radeon AI PRO R9700 for speed.
Which can run bigger models, the Intel Arc Pro B60 or the AMD Radeon AI PRO R9700?
At 32k context the AMD Radeon AI PRO R9700 runs 29 of the models we track fully in memory and the Intel Arc Pro B60 26; only the AMD Radeon AI PRO R9700 holds Kimi Linear 48B-A3B.
Which is faster for local AI, the Intel Arc Pro B60 or the AMD Radeon AI PRO R9700?
On the models both run fully in memory, the AMD Radeon AI PRO R9700 is about 1.5× as fast as the Intel Arc Pro B60 (estimated, median across models).

More comparisons