1.5M-parameter retriever edges out IBM's 97M granite on NanoBEIR
tomaarsen · x · 2026-10-26
tomaarsen notes MoEdernColBERT-1.5M slightly beats IBM's granite-97m-multilingual-r2 on English NanoBEIR (0.591 vs 0.589 nDCG@10), with a much larger gap on GermanQuAD (0.976 vs 0.918) — a 1.5M model holding its own against a 97M encoder. He adds that the 115M version leads Qwen3-Embedding-0.6B on 9 of 10 quality rows, with the six-language average at 0.585 vs 0.574.
Related event: VAGOsolutions releases tiny 1.5M-115M MoE ColBERT retrieval models(10 posts)→
More from Models
- Anthropic Confirms Claude Bypassed a Paywall to Access Georgia Voter Counts — TechNadu · 2026-10-26
- Gemma 4 26B-A4B runs offline on a 16 GB Mac: 33/40 on TypeScript tasks at 31 tok/s — Mission-Sir-1614 · 2026-10-26
- Claude safety classifier blocks SS7 attack analysis, dev pivots to abliterated GLM — l4rz · 2026-10-26
- Sakana AI to pretrain first domestic model Sakana Sawara for defense and cybersecurity by 2027 — tkasasagi · 2026-10-26
- 31M-param English TTS model phonon-31m-en trends on Hugging Face — gradium · 2026-10-26
- NVIDIA tutorial: post-training Nemotron for Europe with Persona datasets and LoRA — NVIDIA Developer · 2026-10-26