Apple's fastest laptop and the one to buy for local AI on the move: with the 40-core GPU and 128GB it generates text from a 7B model at about 120 tokens a second and holds models no laptop graphics card can. Its bigger cooler keeps the M5 Max at full speed, and it runs Cyberpunk 2077 at 1080p Ultra past 100 fps in Notebookcheck's test - but the base 32-core, 36GB model is a far smaller AI machine than the reviewed one.
Against the line-up
Geekbench 6 CPU
Geekbench 6 CPU
Geekbench 6 GPU
Blender Benchmark
Geekbench AI
The whole MacBook Pro line-up side by side, with prices
Every benchmark
Quoted from the publications that ran them; we don't test hardware ourselves. Figures from different publications were run on different systems and scenes, so compare within a row's source.
Cyberpunk 2077
| Setting | Result | Source |
|---|---|---|
| 1080p Ultra |
103fps | Notebookcheck, Aug 27, 2026 MacBook Pro 16 M5 Max, 18-core CPU, 40-core GPU, 48GB 1920 x 1080, Ultra preset, FSR off |
Local LLM (llama.cpp / Ollama)
| Setting | Result | Source |
|---|---|---|
| Llama 2 7B Q4_0, Generation |
120tok/s | llama.cpp community benchmarks (GitHub), Oct 19, 2026 Apple M5 Max, 40-core GPU, 614GB/s (the 40-core option; the table has no 32-core figure) llama-bench tg128 (generating 128 tokens), all layers on the GPU. |
| Llama 2 7B Q4_0, Prompt processing |
3,220tok/s | llama.cpp community benchmarks (GitHub), Oct 19, 2026 Apple M5 Max, 40-core GPU, 614GB/s (the 40-core option; the table has no 32-core figure) llama-bench pp512 (reading a 512-token prompt), all layers on the GPU. |
Geekbench AI
| Setting | Result | Source |
|---|---|---|
| Core ML Neural Engine, Quantized |
58,616points | Macworld, Mar 9, 2026 MacBook Pro 16 M5 Max, 40-core GPU, 128GB, 4TB Quantized score, from Macworld's Geekbench AI Neural Engine chart |
Blender Benchmark
| Setting | Result | Source |
|---|---|---|
| Standard run |
6,462samples/min | Blender Open Data, Oct 19, 2026 Apple M5 Max (GPU - 32 cores), Metal, Blender 5.2.0 Median score over the three scenes, 11 submitted runs. Blender Open Data lists by chip, not by Mac. |
Geekbench 6 CPU
| Setting | Result | Source |
|---|---|---|
| Multi-core |
30,057points | Notebookcheck, Aug 27, 2026 MacBook Pro 16 M5 Max, 18-core CPU, 40-core GPU, 48GB Geekbench 6.7 |
| Single-core |
4,336points | Notebookcheck, Aug 27, 2026 MacBook Pro 16 M5 Max, 18-core CPU, 40-core GPU, 48GB Geekbench 6.7 |
Geekbench 6 GPU
| Setting | Result | Source |
|---|---|---|
| Metal |
224,987points | Notebookcheck, Aug 27, 2026 MacBook Pro 16 M5 Max, 18-core CPU, 40-core GPU, 48GB Geekbench 6.7 GPU, Metal |
3DMark Steel Nomad
| Setting | Result | Source |
|---|---|---|
| Standard run |
4,386points | Notebookcheck, Aug 27, 2026 MacBook Pro 16 M5 Max, 18-core CPU, 40-core GPU, 48GB |
Cinebench 2024
| Setting | Result | Source |
|---|---|---|
| Multi-core |
2,490points | Notebookcheck, Aug 27, 2026 MacBook Pro 16 M5 Max, 18-core CPU, 40-core GPU, 48GB |
Sources
- Blender Open Data (results database)
- Macworld (review)
- Notebookcheck (review)
- llama.cpp community benchmarks (GitHub) (results database)
As an Amazon Associate we earn from qualifying purchases, and we may earn from other shop links. Amazon's price is on Amazon; Best Buy's is read from Best Buy and shown with the time it was checked.