RAGU's 7B model beats Qwen2.5-32B by 12.5% on knowledge-graph construction.

arXiv 2607.11683 splits GraphRAG into separate entity-extraction and consolidation stages using DBSCAN-backed deduplication, LLM summarization and Leiden community detection instead of a single pass. Meno-Lite-0.1 (7B) exceeds Qwen2.5-32B by +12.5% relative harmonic mean on KG construction while matching it on English GraphRAG, and hits 0.84 evidence recall on GraphRAG-Bench Medical versus HippoRAG2's ≤0.76. Runs on one GPU, installs via pip. Directly usable GraphRAG results are rare enough that I'm going to try this one.