readygpu

Intel Arc Pro B60 vs Mac mini M4 32GB

For running models locally, priced in Germany. At 32k context the first runs 26 models fully in memory, the second 24.

In short

The Mac mini M4 32GB has more memory for models: 32 GB against 24 GB. At 32k context the Intel Arc Pro B60 runs 26 of the models we track fully in memory and the Mac mini M4 32GB 24; only the Intel Arc Pro B60 holds Qwen 3.6 35B-A3B. On the models both run fully in memory, the Intel Arc Pro B60 is about 2.9× as fast as the Mac mini M4 32GB (estimated, median across models). In Germany the Intel Arc Pro B60 costs 1.074 € at eBay and the Mac mini M4 32GB 1.400 € at eBay (used): the Intel Arc Pro B60 is 326 € cheaper.

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

Intel Arc Pro B60

1.074 €

eBay

Add to build
Mac mini M4 32GB

1.400 €

eBay, used (asking)

Add to build

Specifications

SpecIntel Arc Pro B60Mac mini M4 32GB
GPUArc Pro B60–
Memory24 GB GDDR6–
Memory bus192-bit128-bit
Memory bandwidth456 GB/s120 GB/s
FP16 compute98.5 TFLOPS3.76 TFLOPS
SoftwareSYCL / oneAPIMetal
Board power200 W–
PCIe generationGen 5–
PCIe lanesx8–
Chip–Apple M4 (10-core GPU)
Unified memory–32 GB
GPU can use by default–21.3 GB
GPU can use, tuned–24 GB
Operating system–macos
Processor–M4 10-core
Storage–512 GB

What each runs

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

ModelIntel Arc Pro B60Mac mini M4 32GB
Qwen 3.8 27B10tok/sUD-Q5_K_M4tok/sUD-Q4_K_M
Qwen 3.6 27B11tok/sQ5_K_M4tok/sQ5_K_M
Gemma 4 31B10tok/sQ4_K_M4tok/sQ4_K_M
Qwen 3.6 35B-A3B49tok/sUD-Q4_K_Mwon't run
Qwen 3.5 27B10tok/sQ5_K_M4tok/sQ5_K_M
Gemma 4 26B-A4B30tok/sUD-Q5_K_M13tok/sUD-Q4_K_M
Qwen 3.5 35B-A3B49tok/sQ4_K_Mwon't run
GLM 4.7 Flash24tok/sQ5_K_M10tok/sQ4_K_M
Devstral Small 2 24B10tok/sQ5_K_M4tok/sQ4_K_M
gpt-oss 20B39tok/sMXFP415tok/sMXFP4
Qwen3 Coder 30B-A3B25tok/sQ4_K_M9tok/sQ4_K_M
Gemma 4 12B17tok/sQ8_06tok/sQ8_0
Qwen 3.5 9B21tok/sQ8_07tok/sQ8_0
Mistral Small 3.2 24B10tok/sQ5_K_M4tok/sQ4_K_M
Gemma 3 27B10tok/sQ5_K_M4tok/sQ4_K_M
Ministral 3 14B12tok/sQ8_04tok/sQ8_0
Qwen3 14B11tok/sQ8_04tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B17tok/sQ8_06tok/sQ8_0
Qwen3 8B17tok/sQ8_06tok/sQ8_0
Phi-4 14B10tok/sQ8_04tok/sQ6_K
Qwen 3.5 4B41tok/sQ8_014tok/sQ8_0
Ministral 3 8B17tok/sQ8_06tok/sQ8_0
Granite 4.2 8B16tok/sQ8_05tok/sQ8_0
Gemma 4 E4B25tok/sQ8_09tok/sQ8_0
LFM2.5 8B-A1B47tok/sQ8_018tok/sQ8_0
Llama 3.1 8B21tok/sQ6_K7tok/sQ6_K
Qwen 3.5 122B-A10Boffloadwon't run
Qwen3 Coder Nextoffloadwon't run
Mistral Small 4 119Boffloadwon't run
GLM 4.5 Airoffloadwon't run
Qwen3 Next 80B-A3Boffloadwon't run
Nemotron 3.5 Lightning 30B-A3Boffloadwon't run
Kimi Linear 48B-A3Boffloadwon't run
Qwen3 32Boffloadwon't run
DeepSeek R1 Distill Qwen 32Boffloadwon'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
Llama 3.3 70Bwon't runwon't run

Questions

Which is better for local AI, the Intel Arc Pro B60 or the Mac mini M4 32GB?
Choose the Intel Arc Pro B60 to run bigger models. Choose the Intel Arc Pro B60 for speed. Choose the Intel Arc Pro B60 to spend less.
Which can run bigger models, the Intel Arc Pro B60 or the Mac mini M4 32GB?
At 32k context the Intel Arc Pro B60 runs 26 of the models we track fully in memory and the Mac mini M4 32GB 24; only the Intel Arc Pro B60 holds Qwen 3.6 35B-A3B.
Which is faster for local AI, the Intel Arc Pro B60 or the Mac mini M4 32GB?
On the models both run fully in memory, the Intel Arc Pro B60 is about 2.9× as fast as the Mac mini M4 32GB (estimated, median across models).
What is the price difference between the Intel Arc Pro B60 and the Mac mini M4 32GB?
In Germany the Intel Arc Pro B60 costs 1.074 € at eBay and the Mac mini M4 32GB 1.400 € at eBay (used): the Intel Arc Pro B60 is 326 € cheaper.

More comparisons