AISwift★ 203
uncSoft/anubis-oss
ANUBIS: BENCHMARK LLM ON APPLE SILICON
anubis-oss — Swift utility for local LLM launch and benchmarking on Apple Silicon. It measures speed and accuracy of GPU inference, comparing results with CPU baseline and outputting metrics in JSON/CSV.
// KEY FEATURES
- Runs local LLMs (Llama, Mistral) on Apple Silicon via Metal GPU for inference.
- Measures latency, throughput and tokens/sec across batch sizes and context lengths.
- Compares GPU results with CPU baseline, generating reports in JSON and CSV formats.
- Lets you configure model parameters via CLI (temperature, top‑k, quantisation).
#apple-silicon#benchmarking#gpu#inference#llm#local-llm#macos#mlx#native#ollama#performance#swiftui
Open on GitHub →New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram