GraphCanon updated Sep 20, 2026 · GitHub synced Sep 20, 2026
Decision brief
Unverified catalog guidance: whichllm is designed to help users identify and benchmark local large language models that perform well on their specific hardware configuration via real-time benchmarks.
Good fit when
- Unverified catalog guidance: When you need to quickly discover which locally available LLM runs most efficiently on your Apple Silicon or GPU infrastructure using Python scripts
- Unverified catalog guidance: If the evaluation based on live, recent benchmarks is more important than considering only the model parameters for decision making
Avoid when
- Unverified catalog guidance: In scenarios where extensive customization of benchmarking criteria beyond what this tool offers is required
- Unverified catalog guidance: When you are working in a non-Python environment and prefer not to introduce Python scripts into your workflow
Observed Jul 17, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Very active (0d since push)
- As of Sep 20, 2026
- Provenance
- Not a fork · Personal account
- As of Sep 20, 2026
- Security (OSV)
- No lockfile
- As of Jul 15, 2026
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install whichllmREADME installation instruction · observed Sep 20, 2026
PyPISimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
A Python-based CLI tool for discovering which local large language models run best on your hardware through real-time benchmarks.
Capability facts
- CLI
- Unknown; CLI entrypoint not verified
Source: pyproject.toml:[project.scripts] · Sep 20, 2026
- Languages
- python
Source: github.language+pyproject.toml · Sep 20, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Tags
README
Quick start Run the recommendation command once, with no project setup. Simulate a GPU before you buy hardware. Install it when you use it often. Other install paths. Auto pick the best model for your hardware and chat whichllm run Auto detect hardware and show best models whichl...
For agents
This page has a .md twin and JSON over the API.