Skip to content

[GitHub Trending] Andyyyy64/whichllm

7.2 relevance
Score Breakdown
technical depth
7
novelty
7
actionability
9
community
6
strategic
5
personal
8

Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.

Local LLM benchmarking tool is highly actionable and relevant to AI/ML practitioners.

AI/ML github.com
Find the local LLM that actually runs and performs best on your hardware. Ranked by real, recency-aware benchmarks, not parameter count. One command, run it instantly. - Andyyyy64/whichllm
Summary

Whichllm is a CLI tool that auto-detects your GPU/CPU/RAM and ranks the best local LLMs from HuggingFace based on real benchmark scores (LiveBench, Aider, Chatbot Arena ELO) rather than just VRAM fit. It supports one-command chat, code snippet generation, and hardware simulation (e.g., `--gpu "RTX 4090"`) to evaluate models before purchasing hardware. The tool uses architecture-aware VRAM and speed estimates, discounts stale or fabricated benchmark claims, and outputs JSON for scripting pipelines.

Author

Andyyyy64