SOURCE-LINKED INTELLIGENCE

Broken on Arrival: Silently Defective LLM Artifacts in Public Model Registries and How to Catch Them

arXiv · AI, language, vision and robotics · article · Sep 5, 2026 · UTC

Developers increasingly run large language models locally by pulling quantized GGUF artifacts from public registries, yet nothing in the distribution pipeline functionally tests these conversions before they reach users. We executed 327 quantized code-capable model artifacts: 305 from the official Ollama library, spanning 15 model lines at every eligible quantization level at or under 8 GB, and 22 from the most-downloaded community repositories on HuggingFace. Each ran a 15-task smoke suite calibrated so that healthy artifacts pass while a known-broken one fails; suspects then faced full 164-t

Read original source ↗ Open in workspace

recordType

paper

region

Global