john-rocky/apple-silicon-llm-bench

Community benchmark database for running LLMs on Apple Silicon Macs

Benchmarks comparing PyTorch and MLX on Apple Silicon GPUs

Swift + Metal MoE inference for Apple Silicon: Qwen 3.6 35B at 23.5–29.3 tok/s decode with 2.20× faster long-prompt prefill on a 24 GB M5; Gemma 4 26B in ~2 GB, DeepSeek-V4-Flash 284B, Inkling-Small 276B, native Mac app, CLI, and OpenAI-compatible server.

Benchmark of Apple MLX operations on all Apple Silicon chips (GPU, CPU) + MPS and CUDA.

⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, MACOS + iOS iPhone app.

Multiple NVIDIA GPUs or Apple Silicon for Large Language Model Inference?

Fastest LLM inference runtime for Apple Silicon

Production LLM inference on the Apple Neural Engine — a practitioner's guide, complete with converters, Swift runtimes, and validated model manifests

High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.