OLMo 3
the only model here where 'fully open' survives contact with the evidence — weights, training data, code and checkpoints.
every other entry calls itself open and means the weights. ai2 publishes the training data too — which is worth more than the benchmark places it gives up.
apache 2.0 on the weights, and alongside them the dolma 3 training corpus, the dolci post-training datasets, the training and evaluation code, and the intermediate checkpoints — all linked from the model card. if you need to audit what went into a model, or reproduce it, this is the only real option on this page.
the family is 7b and 32b dense, each in base, instruct, think and rlzero variants, which makes the reasoning-focused ones genuinely useful for research into how these models learn. the 7b runs on a 16-24gb consumer card and the 32b on a single 48-80gb card.
the description above is ours, condensed from the ranking. pricing moves — check it on the vendor's own page before you rely on it.
- category
- open-weight llms
- pricing
- free (apache 2.0)
- website
- huggingface.co
every other entry calls itself open and means the weights. ai2 publishes the training data too — which is worth more than the benchmark places it gives up.
we researched this category against vendors' own pricing pages and licence files. that is where this line comes from — not from the vendor, and not from anything they paid for.