iPhone 17 Pro Max
A flagship smartphone from Apple featuring the A19 Pro chip with an integrated Metal 4 tensor operations unit, enabling on-device AI inference capabilities.
Timeline (last 90 days)
An author chained together two gaming PCs, an M4 Pro MacBook and two iPhone 17 Pro Max devices to run Kun 3.8 Flash Next (a 48-layer MoE model with 512 experts per layer), measuring 37-39 tokens/s at a 60k context.
MiniCPM-V 4.7 35B-A3B achieves a decoding speed of 13+ tokens/s on the iPhone 17 Pro Max.
When unfolded, the width of the foldable iPhone is roughly equivalent to a 17 Pro Max in a leather case, placing it at the edge of comfortable one-handed operation.
A developer connected an iPhone 17 Pro Max to a 24GB-memory M4 Pro MacBook via a 10 Gb/s USB-C cable, using the phone as a second GPU to share the computational load for a locally running Qwen 3.8 27B (IQ4_XS quantization) model.
All Facts (3)
An author chained together two gaming PCs, an M4 Pro MacBook and two iPhone 17 Pro Max devices to run Kun 3.8 Flash Next (a 48-layer MoE model with 512 experts per layer), measuring 37-39 tokens/s at a 60k context.
50%UnverifiedWhen unfolded, the width of the foldable iPhone is roughly equivalent to a 17 Pro Max in a leather case, placing it at the edge of comfortable one-handed operation.
50%UnverifiedA developer connected an iPhone 17 Pro Max to a 24GB-memory M4 Pro MacBook via a 10 Gb/s USB-C cable, using the phone as a second GPU to share the computational load for a locally running Qwen 3.8 27B (IQ4_XS quantization) model.
50%