GitHub - zolotukhin/zinc: Zig INferenCe Engine — Local LLM inference on AMD GPUs and Apple Silicon
Zig INferenCe Engine — Local LLM inference on AMD GPUs and Apple Silicon - zolotukhin/zinc
LLM Benchmarking Platform
Summary
Community-driven benchmarking platform for local LLM inference. Users submit and compare performance metrics like tokens per second, time to first token, and hardware efficiency across GPUs, Apple Silicon, and CPU configurations to find optimal local setups.
Highlights
- Community-submitted benchmarks enable real-world performance comparison across diverse hardware
- Tracks key metrics: tokens per second, time to first token, and overall hardware efficiency
- Covers three major hardware categories: NVIDIA GPUs, Apple Silicon, and CPU-only setups
- Helps users identify cost-effective and optimal configurations for running LLMs locally
auto-generated
Context
Audience
Developers and hobbyists running large language models locally who want to optimize hardware choices and compare real-world performance across different platforms
DomainLocal LLM Inference
Formatinteractive benchmarking platform
Accessfree online
Source Overview
Localmaxxing hosts community-submitted benchmarks for local LLM inference.
Users compare tok/s, TTFT, and hardware efficiency across GPUs, Apple Silicon, and CPU setups. The site tracks speed and helps identify optimal hardware configurations.
Topics
Related
Ollamallama.cppLM StudiovLLMApple Silicon M-series performance
