Dynamically Filter Models for AI Agents via HF CLI

vanstriendaniel · x · 2026-07-15

The author points out that AI Agents often rely on outdated memory when selecting models. Now, agents can fetch the latest, ready-to-run list of models via the Hugging Face CLI command (hf models ls).

This command supports filtering by inference engine (like vLLM, SGLang, llama.cpp, Ollama) and parameter size (e.g., between 4B and 32B). It outputs JSON formatted data, allowing agents to easily parse and pick models that fit the current hardware configuration.

Original post →

More from coding & agent

coding & agent channel →