Mac Studio M5 Max 40-core GPU, 128GB / 512GB
Apple · 128GB memory · new
Prices
US store: $5,099 · list price · checked 2026-10-16 · list price as of 2026-10-16 (source) · Go to store · Check price on Amazon
EU (Ireland): €5,909 · list price · checked 2026-10-16 · list price as of 2026-10-16 (source) · Go to store · Check price on Amazon
USD price history
14 observation(s). History grows with every scheduled check.
EUR price history
13 observation(s). History grows with every scheduled check.
Benchmark
119.08 tok/s on Apple M5 Max 40-core GPU (MacBook Pro 16, 128GB) (Metal), posted 2026-06-22. Source: llama.cpp discussion
Value: 23.4 tok/s per $1,000 · 20.2 per €1,000
Metric: llama.cpp llama-bench, Llama-2 7B Q4_0, tg128 (text generation tok/s); best of FA on/off as posted
Large model (gpt-oss-120b)
79.1 tok/s on Apple M5 Max 40-core, 128GB (MacBook Pro), Ollama 0.34.1 (not llama-bench), 2026-09-16. Source
Value: 15.5 tok/s per $1,000 · 13.4 per €1,000
Related
NVIDIA DGX Spark vs Mac Studio M5 Max 40-core GPU · Mac Studio M5 Max 40-core GPU vs Framework Desktop 128GB · Mac Studio M5 Max 40-core GPU vs MacBook Pro 16" M5 Max 40-core GPU · Mac Studio M5 Ultra 80-core GPU vs Mac Studio M5 Max 40-core GPU · Mac Studio M5 Max 40-core GPU vs GMKtec EVO-X2 128GB / 1TB · Runs Qwen3.8 27B? · Runs Qwen3.6 35B-A3B? · Runs Gemma 4 12B? · Runs Qwen3-Coder 30B-A3B? · Runs Qwen3.5 9B? · Runs Qwen3.6 27B? · Runs Gemma 4 26B-A4B? · Runs Muse Glimmer 30B? · Runs gpt-oss-20b? · Runs gpt-oss-120b? · Runs Qwen3 8B? · Runs Llama 3.1 8B? · Runs Qwen3 32B? · Runs Llama 3.3 70B? · Runs Qwen3.8-Flash-Next? · Runs GLM-5.3-Flash?