open-weight-llm

Find what open-weight Large Language Model (LLM) can fit into your hardware and run it

An independent, evidence-graded read on how much you own the open models and inference providers you rely on.

A systems-security framework for evaluating trust in open-weight LLM deployments — air-gapped environments, hidden backdoors, and software supply chain integrity.

Solving the amnesiac problem for LLM agents. Research series on agents that compound knowledge across sessions — first measurement: +4.6 pp accuracy lift on Terminal-Bench 2.1 with an open-weight executor and a single failure-derived skill file.

Preregistered cross-lingual evidence-sufficiency probing in Qwen3 — 6 languages, 29,206 paired QA constructions, frozen English probes, and a sealed one-shot evaluation.

A custom agent that reviews, fixes, and merges pull requests. Built to leverage Hugging Face's model inference providers for agent orchestration fundamentals.

Regularly updated index of open-weight LLMs—tracking benchmarks, parameter count, context length, and license terms.