⭐ Built in the Agent OS — get it inside the AI Profit BoardroomJoin AIPB →

MLX Speedtest

Apple Silicon Unified Memory Array Benchmark

M3 Max (Unified 128GB)
0.0
Tokens / sec
SYSTEM READY — PRESS RUN TEST
Tensor Bandwidth
0 GB/s
Peak: --
FP16 Compute
0.0 TFLOPS
GEMM Ops
TTFT Latency
0.0 ms
First Token
Quantization
4-Bit Core
MLX Array Engine
Drag mouse / touch to rotate 3D Tensor Core • Scroll to zoom