Guides
Plain-English explainers on the parts of running local LLMs that matter most.
- Local model performance: what makes an LLM fast or slow
Understand speed and memory fit, inspect community reports, measure your setup and diagnose slow inference.
- How to compare local LLM benchmarks
Compare setup conditions, capture a measurement and share a reproducible report with the copyable template.
- Quantization for local LLMs
What Q4_K_M, Q5, MLX-4bit, and the rest actually mean, and how to pick the right one for your hardware.
- VRAM requirements for local LLMs
How much VRAM you actually need, by model size and quantization level. Includes a what-fits-by-tier reference table.
For practical setup and testing workflows, read the llamaperf blog.