llms.blog
Apple Silicon2 articles

Apple Silicon

Articles

  • Local LLM Inference Frameworks in Production: Comparing llama.cpp, Ollama, Apple MLX, and Exo Distributed Clusters

    The deployment landscape for large language models is bifurcating. While datacenter workloads rely on high-throughput continuous batching engines such as vLLM and TensorRT-LLM, local and edge deployments operate under fundamentally different physical constraints. On developer workstations, embedded hardware, and private office clusters, inference is rarely bound by compute saturation across thousands of concurrent requests. Instead, it is constrained by memory bandwidth, local VRAM capacity, hos

    1 min

  • Local LLM Inference on Apple Silicon: Architecture, Unified Memory, and Serving Benchmarks for MLX, llama.cpp, and Ollama

    Local large language model (LLM) serving on consumer hardware has historically faced a hard trade-off between memory capacity and execution bandwidth. Discrete consumer GPUs offer high memory bandwidth (up to 1,008 GB/s on an Nvidia RTX 4090) but are capped at 24 GB of VRAM, requiring model sharding or quantization to fit models beyond 14 billion parameters. Apple Silicon platforms bypass this capacity ceiling through a Unified Memory Architecture (UMA), where the CPU, GPU, and Apple Neural Eng

    1 min