Project AURIONAI Use-Cases Research & Innovation
Allen AI
LLM

OLMo 2 32B (OLMo-2-0325-32B-Instruct)

Ai2 fully open 32B model with released data, code and weights, which Ai2 says outperforms GPT-3.5 Turbo and GPT-4o mini on academic benchmarks.

Allen AIAllen AIUSAOLMo 2Family
Training curves of OLMo 2 32B Instruct over time, from the model card.
Levelmodel
ClassLLM
Parameters32B
Contextnot in the notes
Released13 Mar 2025
Opennessfully open
Runs onnot in the notes
Statusactive

Benchmark Results

vendor-reported
GSM8Kmath
vendor-reported
87.6
050100

Score in %. Higher is better.

OLMo-2-0325-32B-Instruct model cardMar 2025 huggingface.co
IFEvalknowledge and reasoning
vendor-reported
85.6
050100

Score in %. Higher is better.

OLMo-2-0325-32B-Instruct model cardMar 2025 huggingface.co
MATHmath
vendor-reported
49.7
050100

Score in %. Higher is better.

OLMo-2-0325-32B-Instruct model cardMar 2025 huggingface.co
MMLUknowledge and reasoning
vendor-reported
77.3
050100

Score in %. Higher is better.

OLMo-2-0325-32B-Instruct model cardMar 2025 huggingface.co
Where this comes from
Every score names who ran it: vendor-reported, maintainer-run or independent. A rank is shown with the population it was ranked in (gap rule 3).

Lineage

instruct of
OLMo-2-0325-32B to OLMo 2 32B (OLMo-2-0325-32B-Instruct): instruct of, high confidenceOLMo-2-0325-32BOLMo-2-0325-32BAllen AI, Mar 2025OLMo 2 32B (OLMo-2-0325-32B-Instruct)OLMo 2 32B (OLMo-2-0325-32…Allen AI, Mar 2025
Allen AIOLMo-2-0325-32B is the parent (instruct of)high confidencemodel card
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 2 models. Confidence and evidence are the notes' own.

R&D Topics

Data curation and synthetic dataproduced byOpen post-training recipesproduced byOpen-weight frontier releases as research substrateused by

Identity

Developer
Allen AI
Family
OLMo 2
Released
13 Mar 2025 sourcesannouncement page
Weights published
–
Record checked
11 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
dense transformer
Total parameters
32B sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
text
Output
text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
fully open
Licence
Apache License 2.0 sources
Access routes
open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
Primarily English
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Industry Use Cases

No industry use case links this model.

Sources

  1. allenai.org/blog/olmo2-32B https://allenai.org/blog/olmo2-32B
  2. huggingface.co/allenai/OLMo-2-0325-32B-Instruct https://huggingface.co/allenai/OLMo-2-0325-32B-Instruct

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "OLMo 2 32B (OLMo-2-0325-32B-Instruct)", https://aurion.semai.id/models/allen-ai-olmo-2-32b/, records of October 2026.