Hardware · SoC / APU · Apple

Apple M4 Pro (20-core GPU)

Shares one pool of LPDDR5X memory between CPU and GPU at 273 GB/s. What fits depends on how much memory the system has.

What it runs

Largest models without offloading on the Mac mini M4 Pro 48 GB, 8K context.

Variant
Mixtral 8x7B Instruct v0.1
46.7B · Q4_K_M via llama.cpp
Runs well
~21 tok/s est.
Variant
Qwen2.5 32B Instruct
32.8B · Q5_K_M via llama.cpp
Runs well
~7 tok/s est.
Variant
Qwen2.5-Coder 32B Instruct
32.8B · Q4_K_M via llama.cpp
Runs well
~9 tok/s est.
Variant
DeepSeek-R1-Distill-Qwen-32B
32.8B · Q4_K_M via llama.cpp
Runs well
~9 tok/s est.
Variant
Qwen3 30B-A3B
30.5B · Q8_0 via llama.cpp
Tight fit
~44 tok/s est.
Variant
Gemma 3 27B IT
27.4B · Q4_K_M via llama.cpp
Runs well
~10 tok/s est.
Variant
Gemma 2 27B IT
27.2B · Q4_K_M via llama.cpp
Runs well
~10 tok/s est.
Variant
Mistral Small 24B Instruct 2501
23.6B · Q6_K via llama.cpp
Runs well
~9 tok/s est.
Variant
Qwen2.5 14B Instruct
14.8B · Q6_K via llama.cpp
Runs well
~14 tok/s est.
Variant
Phi-4
14.7B · Q8_0 via llama.cpp
Runs well
~11 tok/s est.

System Mac mini M4 Pro 48 GB
Runs models up to ~57B parameters at 4-bit in unified memory. What runs

Throughput on systems containing this device.

No performance measurements recorded yet.

Contributions are not open yet, so there is nothing here from members.

Contributions are not open yet, so there is nothing here from members.

No source records linked.