readygpu

Mac mini M4 16GB vs Mac mini M4 32GB

For running models locally, priced in Germany. At 8k context the first runs 13 models fully in memory, the second 26.

In short

The Mac mini M4 32GB has more memory for models: 32 GB against 16 GB. At 8k context the Mac mini M4 32GB runs 26 of the models we track fully in memory and the Mac mini M4 16GB 13; only the Mac mini M4 32GB holds Qwen 3.8 27B. On the models both run fully in memory, the Mac mini M4 16GB and the Mac mini M4 32GB are about as fast as each other (estimated). In Germany the Mac mini M4 16GB costs 800 € at eBay and the Mac mini M4 32GB 1.400 € at eBay (used): the Mac mini M4 16GB is 600 € cheaper.

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

Mac mini M4 16GB

800 €

eBay

Add to build
Mac mini M4 32GB

1.400 €

eBay, used (asking)

Add to build

Specifications

SpecMac mini M4 16GBMac mini M4 32GB
ChipApple M4 (10-core GPU)Apple M4 (10-core GPU)
Memory bus128-bit128-bit
Memory bandwidth120 GB/s120 GB/s
FP16 compute3.76 TFLOPS3.76 TFLOPS
SoftwareMetalMetal
Unified memory16 GB32 GB
GPU can use by default10.7 GB21.3 GB
GPU can use, tuned10.666666666666666 GB24 GB
Operating systemmacosmacos
ProcessorM4 10-coreM4 10-core
Storage256 GB512 GB

What each runs

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

ModelMac mini M4 16GBMac mini M4 32GB
Qwen 3.8 27Bwon't run4tok/sUD-Q5_K_M
Qwen 3.6 27Bwon't run4tok/sQ5_K_M
Gemma 4 31Bwon't run4tok/sQ4_K_M
Qwen 3.5 27Bwon't run4tok/sQ5_K_M
Gemma 4 26B-A4Bwon't run13tok/sUD-Q5_K_M
Devstral Small 2 24Bwon't run4tok/sQ6_K
GLM 4.7 Flashwon't run12tok/sQ5_K_M
Qwen3 Coder 30B-A3Bwon't run18tok/sQ4_K_M
gpt-oss 20Bwon't run18tok/sMXFP4
Qwen3 32Bwon't run4tok/sQ4_K_M
Gemma 4 12B8tok/sQ6_K6tok/sQ8_0
Qwen 3.5 9B8tok/sQ8_08tok/sQ8_0
DeepSeek R1 Distill Qwen 32Bwon't run4tok/sQ4_K_M
Gemma 3 27Bwon't run4tok/sQ5_K_M
Mistral Small 3.2 24Bwon't run4tok/sQ6_K
Ministral 3 14B8tok/sQ4_K_M5tok/sQ8_0
Qwen3 14B8tok/sQ4_K_M5tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B8tok/sQ8_08tok/sQ8_0
Qwen3 8B8tok/sQ8_08tok/sQ8_0
Phi-4 14B7tok/sQ4_K_M5tok/sQ8_0
Qwen 3.5 4B16tok/sQ8_016tok/sQ8_0
Ministral 3 8B8tok/sQ8_08tok/sQ8_0
Granite 4.2 8B7tok/sQ8_07tok/sQ8_0
Gemma 4 E4B9tok/sQ8_09tok/sQ8_0
LFM2.5 8B-A1B32tok/sQ8_032tok/sQ8_0
Llama 3.1 8B10tok/sQ6_K10tok/sQ6_K
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
Qwen 3.5 122B-A10Bwon't runwon't run
Nemotron 3 Super 120B-A12Bwon't runwon't run
Qwen3 Coder Nextwon't runwon't run
gpt-oss 120Bwon't runwon't run
Mistral Small 4 119Bwon't runwon't run
Qwen 3.6 35B-A3Bwon't runwon't run
GLM 4.5 Airwon't runwon't run
Qwen 3.5 35B-A3Bwon't runwon't run
Qwen3 Next 80B-A3Bwon't runwon't run
Nemotron 3.5 Lightning 30B-A3Bwon't runwon't run
Kimi Linear 48B-A3Bwon't runwon't run
Llama 3.3 70Bwon't runwon't run

Questions

Which is better for local AI, the Mac mini M4 16GB or the Mac mini M4 32GB?
Choose the Mac mini M4 32GB to run bigger models. Choose the Mac mini M4 16GB to spend less.
Which can run bigger models, the Mac mini M4 16GB or the Mac mini M4 32GB?
At 8k context the Mac mini M4 32GB runs 26 of the models we track fully in memory and the Mac mini M4 16GB 13; only the Mac mini M4 32GB holds Qwen 3.8 27B.
Which is faster for local AI, the Mac mini M4 16GB or the Mac mini M4 32GB?
On the models both run fully in memory, the Mac mini M4 16GB and the Mac mini M4 32GB are about as fast as each other (estimated).
What is the price difference between the Mac mini M4 16GB and the Mac mini M4 32GB?
In Germany the Mac mini M4 16GB costs 800 € at eBay and the Mac mini M4 32GB 1.400 € at eBay (used): the Mac mini M4 16GB is 600 € cheaper.

More comparisons