The Open-Source AI Stack
RSS
All hardware

Hardware · Apple unified

Apple MacBook Air (M5)

Apple

Fanless thin-and-light; fine for small models, bandwidth-starved for large ones. The lower end of the Apple unified-memory range.

CPU · GPU · NPU 153 GB/s memory bus 32 GB Unified memory
Apple unified. Bus width tracks bandwidth (153 GB/s, sets decode speed); the box tracks capacity (32 GB, sets what fits). Unified memory is one pool shared by CPU and accelerator.

Specs

Memory
32 GB Unified LPDDR5X
Bandwidth
153 GB/s
Power
20 W
Form factor
soc
Interconnect
none
Released
2026-03

What it runs (single unit, Q4_K_M, 4K context)

Model Fits? Decode ceiling
Llama 3.1 8B Instruct yes ~30 tok/s
Llama 3.3 70B Instruct no —
Qwen 2.5 72B Instruct no —
DeepSeek-V3 no —

Ceiling is the theoretical rooflineruntimeA performance model that bounds throughput by either compute or memory bandwidth, whichever is the limiting resource for an operation's arithmetic intensity. Open full entry ; open the explorer to set quant, context, and runtime and see the realistic range.

Sources