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The author points out that AI Agents often rely on outdated memory when selecting models.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.
More from coding & agent
- Marker 2 claims better quality than MinerU and docling while hitting 27 pages/sec — VikParuchuri · 2026-07-21
- Marker 2 launches with PDF-to-Markdown support and claims up to 27 pages/sec — VikParuchuri · 2026-07-21
- Cursor publishes a strong deep dive on agent swarms for coding workflows — Sam_Witteveen · 2026-07-21
- A deleted NanoGPT PR still propagated into later world-record submissions — yacineMTB · 2026-07-21
- Soft Clamp cuts tool-call overuse in multi-teacher distillation, from 13.7% to 9.0% — antgroup · 2026-07-21
- Agent harness memory loss and compaction are still a major usability problem — adityaag · 2026-07-21