{"data":{"slug":"andyyyy64-whichllm","name":"whichllm","tagline":"Command-line tool to find and benchmark local LLM performance","github_url":"https://github.com/Andyyyy64/whichllm","owner":"Andyyyy64","repo":"whichllm","owner_avatar_url":"https://avatars.githubusercontent.com/u/105579829?v=4","primary_language":"Python","stars":6666,"forks":368,"topics":["localllm"],"archived":false,"github_pushed_at":"2026-09-19T16:22:49+00:00","maintenance_label":"Very active","stars_delta_30d":441,"url":"https://www.graphcanon.com/tools/andyyyy64-whichllm","markdown_url":"https://www.graphcanon.com/tools/andyyyy64-whichllm.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/andyyyy64-whichllm","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=andyyyy64-whichllm","description":"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.","homepage_url":null,"license":"MIT","open_issues":13,"watchers":25,"ai_summary":"A Python-based CLI tool for discovering which local large language models run best on your hardware through real-time benchmarks.","readme_excerpt":"## Quick start\n\nRun the recommendation command once, with no project setup.\n\n```bash\nuvx whichllm@latest\n```\n\nSimulate a GPU before you buy hardware.\n\n```bash\nuvx whichllm@latest --gpu \"RTX 4090\"\n```\n\nInstall it when you use it often.\n\n```bash\nuv tool install whichllm\nuv tool upgrade whichllm  # update an existing install\n```\n\nOther install paths.\n\n```bash\nbrew install andyyyy64/whichllm/whichllm\npip install whichllm\n```\n\n---\n\n# Auto-pick the best model for your hardware and chat\nwhichllm run\n\n---\n\n# Auto-detect hardware and show best models\nwhichllm\n\n---\n\n# Show hardware info only\nwhichllm hardware\n\n---\n\n# Plan: what GPU do I need for a specific model?\nwhichllm plan \"llama 3 70b\"\nwhichllm plan \"Qwen2.5-72B\" --quant Q8_0\nwhichllm plan \"mistral 7b\" --context-length 32768\n\n---\n\n## Requirements\n\n- Python 3.11+\n- NVIDIA GPU detection via `nvidia-ml-py` (included by default)\n- AMD / Apple Silicon detected automatically","github_created_at":"2026-03-04T13:16:00+00:00","created_at":"2026-07-15T10:58:05.126602+00:00","updated_at":"2026-09-20T04:58:59.234204+00:00","categories":[{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"},{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"}],"tags":[{"slug":"ai","name":"ai"},{"slug":"apple-silicon","name":"apple-silicon"},{"slug":"benchmarks","name":"benchmarks"},{"slug":"cli","name":"cli"},{"slug":"huggingface","name":"huggingface"},{"slug":"inference","name":"inference"},{"slug":"llm","name":"llm"},{"slug":"local-llm","name":"local-llm"}],"trust":{"provenance":{"is_fork":false,"github_id":1172574522,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T04:58:56.435Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":7,"days_since_push":0,"last_release_at":"2026-09-19T16:22:50Z","stars_delta_30d":441,"open_issues_delta_30d":-9},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-15T10:58:06.324Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T04:58:57.480Z"},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-09-20T04:58:57.480Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-09-20T04:58:57.480Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-20T04:58:57.480Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need to quickly discover which locally available LLM runs most efficiently on your Apple Silicon or GPU infrastructure using Python scripts","If the evaluation based on live, recent benchmarks is more important than considering only the model parameters for decision making"],"when_not_to_use":["In scenarios where extensive customization of benchmarking criteria beyond what this tool offers is required","When you are working in a non-Python environment and prefer not to introduce Python scripts into your workflow"],"source":"enrich:decision_facts","observed_at":"2026-07-17T10:11:20.099Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"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."}]}}