0.5B base model trained on 60B tokens rivals Qwen3.5-2B trained on 30T+ tokens

AZDR 11 points 2 comments November 13, 2026
huggingface.co · View on Hacker News

Discussion Highlights (1 comments)

cobychapple

it's 2.59B total with 553M active, so "0.5B vs 2B" more like 2.5B vs 2B? the card's own table has OLMo-2 1B (61.1) beating both.

Semantic search powered by Rivestack pgvector
12,728 stories · 120,417 chunks indexed