readygpu

Intel Arc Pro B60 vs Mac mini M4 16GB

For running models locally, priced in Germany. At 8k context the first runs 56 models fully in memory, the second 30.

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 56 of the models we track fully in memory and the Mac mini M4 16GB 30; only the Intel Arc Pro B60 holds Qwen 3.8 27B. On the models both run fully in memory, the Intel Arc Pro B60 is about 2.9× as fast as the Mac mini M4 16GB (estimated, median across models). In Germany the Intel Arc Pro B60 costs 1.074 € at eBay and the Mac mini M4 16GB 800 € at eBay: the Mac mini M4 16GB is 274 € cheaper.

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

Intel Arc Pro B60

1.074 €

eBay

Add to build
Mac mini M4 16GB

800 €

eBay

Add to build

Specifications

SpecIntel Arc Pro B60Mac mini M4 16GB
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–16 GB
GPU can use by default–10.7 GB
GPU can use, tuned–10.666666666666666 GB
Operating system–macos
Processor–M4 10-core
Storage–256 GB

What each runs

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

ModelIntel Arc Pro B60Mac mini M4 16GB
Qwen 3.8 27B10tok/sUD-Q6_Kwon't run
Qwen 3.6 27B10tok/sQ6_Kwon't run
Gemma 4 31B10tok/sQ5_K_Mwon't run
Qwen 3.6 35B-A3B60tok/sQ4_K_Mwon't run
Qwen 3.5 27B10tok/sQ6_Kwon't run
Gemma 4 26B-A4B32tok/sUD-Q6_Kwon't run
Qwen 3.5 35B-A3B61tok/sQ4_K_Mwon't run
GLM 4.7 Flash31tok/sQ5_K_Mwon't run
Devstral Small 2 24B11tok/sQ6_Kwon't run
Nemotron 3.5 Lightning 30B-A3B54tok/sMXFP4won't run
gpt-oss 20B48tok/sMXFP4won't run
Qwen3 Coder 30B-A3B43tok/sQ5_K_Mwon't run
Qwen3 32B10tok/sQ4_K_Mwon't run
Gemma 4 12B17tok/sQ8_08tok/sQ6_K
Qwen 3.5 9B23tok/sQ8_08tok/sQ8_0
Mistral Small 3.2 24B11tok/sQ6_Kwon't run
DeepSeek R1 Distill Qwen 32B10tok/sQ4_K_Mwon't run
Gemma 3 27B10tok/sQ6_Kwon't run
Ministral 3 14B15tok/sQ8_08tok/sQ4_K_M
Qwen3 14B13tok/sQ8_08tok/sQ4_K_M
DeepSeek R1 0528 Qwen3 8B23tok/sQ8_08tok/sQ8_0
Qwen3 8B23tok/sQ8_08tok/sQ8_0
Phi-4 14B13tok/sQ8_07tok/sQ4_K_M
Qwen 3.5 4B48tok/sQ8_016tok/sQ8_0
Ministral 3 8B22tok/sQ8_08tok/sQ8_0
Granite 4.2 8B21tok/sQ8_07tok/sQ8_0
Gemma 4 E4B27tok/sQ8_09tok/sQ8_0
LFM2.5 8B-A1B86tok/sQ8_032tok/sQ8_0
Llama 3.1 8B30tok/sQ6_K10tok/sQ6_K
Qwen2.5 0.5B361tok/sQ8_0124tok/sQ8_0
Qwen3.5 0.8B245tok/sQ8_084tok/sQ8_0
Qwen3.5 2B147tok/sQ5_K_M50tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B107tok/sQ8_037tok/sQ8_0
MiniCPM5 2B75tok/sQ8_026tok/sQ8_0
LFM2.5 2.6B68tok/sQ8_023tok/sQ8_0
LFM2.5 VL 3B68tok/sQ8_023tok/sQ8_0
Spark X2.5 4B67tok/smlx-4bit23tok/smlx-4bit
granite vision 4.1 4b53tok/sQ8_018tok/sQ8_0
LFM2.5 24B A2B52tok/sQ6_Kwon't run
granite 4.2 3b50tok/sQ8_017tok/sQ8_0
Mellum2.1 12B A2.5B Thinking45tok/sQ8_021tok/sQ5_K_M
Kimi VL A3B Thinking 250637tok/sQ8_0won't run
Kimi VL A3B36tok/smlx-8bitwon't run
DeepSeek R1 Distill Qwen 7B27tok/sQ8_09tok/sQ8_0
GLM 4 9B 041427tok/smlx-5bit9tok/smlx-5bit
DeepSeek R1 Distill Llama 8B24tok/sQ8_08tok/sQ8_0
Ministral 3 8B Reasoning 251222tok/sQ8_08tok/sQ8_0
GLM 4.6V Flash22tok/sQ8_08tok/sQ8_0
GLM 4.1V 9B Thinking19tok/smlx-8bitwon't run
DeepSeek R1 Distill Qwen 14B13tok/sQ8_07tok/sQ4_K_M
Devstral Small 250713tok/sQ5_K_Mwon't run
Magistral Small 250713tok/sQ5_K_Mwon't run
Magistral Small 250913tok/sQ5_K_Mwon't run
Magistral Small 250611tok/sQ6_Kwon't run
Qwen3.8 27B OBLITERATED11tok/smlx-4bitwon't run
granite 4.2 30b10tok/sQ5_K_Mwon't run
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
Kimi Linear 48B-A3Boffloadwon't run
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 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

Questions

Which is better for local AI, the Intel Arc Pro B60 or the Mac mini M4 16GB?
Choose the Intel Arc Pro B60 to run bigger models. Choose the Intel Arc Pro B60 for speed. Choose the Mac mini M4 16GB to spend less.
Which can run bigger models, the Intel Arc Pro B60 or the Mac mini M4 16GB?
At 8k context the Intel Arc Pro B60 runs 56 of the models we track fully in memory and the Mac mini M4 16GB 30; only the Intel Arc Pro B60 holds Qwen 3.8 27B.
Which is faster for local AI, the Intel Arc Pro B60 or the Mac mini M4 16GB?
On the models both run fully in memory, the Intel Arc Pro B60 is about 2.9× as fast as the Mac mini M4 16GB (estimated, median across models).
What is the price difference between the Intel Arc Pro B60 and the Mac mini M4 16GB?
In Germany the Intel Arc Pro B60 costs 1.074 € at eBay and the Mac mini M4 16GB 800 € at eBay: the Mac mini M4 16GB is 274 € cheaper.

More comparisons