Skip to content

[GitHub Trending] Andyyyy64/whichllm

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

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

Tool to benchmark local LLMs is highly actionable and relevant to AI/ML workflows.

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 auto-detects GPU/CPU/RAM and ranks HuggingFace models by benchmark quality (LiveBench, Aider, ELO) not just VRAM fit, using architecture-aware estimates for speed and memory. It runs via uvx or pip, simulates GPUs like RTX 4090, and offers one-command chat and scriptable JSON output. The tool demotes stale leaderboards and rejects fabricated scores, ensuring recommendations reflect current-generation models like Qwen3.6-27B.

Author

Andyyyy64