Spin-transfer torque random-access memory (STT-RAM) is gaining momentum as a promising technology for high-density and embedded nonvolatile memory. Owing to random thermal fluctuations, switching transitions generally display statistical variations from cycle to cycle. Stochastic variations are critical to the hindering of memory and computing applications of STT-RAM. To enable the design of STT-RAM circuits for memory and computing, there is a need for accurate compact models capable of predicting the stochastic behavior. Here, we present a detailed model accounting for the anomalous thermal regime of switching deviating from the Néel-Brown thermal model below 200 ns. Anomalous switching is explained by the nonlinear lowering of the energy barrier associated with the perpendicular magnetic anisotropy (PMA). The model is extensively verified against the write-error-rate (WER) data as a function of applied voltage and pulsewidth and experimental switching time-delay distributions. Index Terms-Magnetic tunnel junction (MTJ), spintransfer torque magnetoresistive RAM (STT-MRAM), stochastic switching, switching variability modeling. I. INTRODUCTION S PIN-TRANSFER TORQUE random-access memory (STT-RAM) is attracting a strong interest because of the storage-class memory (SCM) [1]-[5], dynamic RAM (DRAM) replacement [6], and embedded nonvolatile memory [6]-[8] due to its fast switching [9], nonvolatile states, high endurance [10], CMOS compatibility, and low-current operation [11]. STT-RAM and spintronic devices in general find application also in novel non-von Neumann concepts of computing,