/shelf
/local llm tools
Ollama, LM Studio, llama.cpp — run models on your machine. 2 entries cached.
filter:
all (2)
desktop-app (1)gui (1)linux (1)llama (1)lm-studio (1)local-llm (2)macos (2)mistral (1)model-browser (1)ollama (1)openai-compatible (2)runtime (1)
★ featured
★ featured / fresh
Ollama
Run large language models locally with a single command. Ollama handles model downloads, quantization, and an OpenAI-compatible API — the fastest way to run Llama, Mistral, Gemma, and Phi locally.
❯ npx cache add ollama
resolving dependencies…
✓ fetched manifest
✓ verified signature (sha256)
✓ installed to ~/.cache/ollama
─────────────────────────────────
Ollama MIT
❯ ▊
all entries 1 shown
# machine-readable
curl cache.directory/local-llm/rss.xml
curl cache.directory/api/v1/local-llm.json
curl cache.directory/api/v1/local-llm.json