Allen Institute/Dense

OLMo-2-0325-32B

Name: OLMo-2-0325-32B
Author: Allen Institute

OLMo 2 32B Instruct March 2025 is post-trained variant of the OLMo-2 32B March 2025 model, which has undergone supervised finetuning on an OLMo-specific variant of the Tülu 3 dataset, further DPO training on this dataset, and final RLVR training o...

chat

32.2B

Parameters

Context length

Benchmarks

Quantizations

HF downloads

Architecture

Dense

Released

2025-06-15

Layers

KV Heads

Head Dim

128

Family

olmo

Quantization Options

Quant	Bits	VRAM @ 4K	Quality
IQ3_XXS	3.25	13.6 GB	low
IQ3_XS	3.5	14.6 GB	low
Q3_K_S	3.64	15.1 GB	low
IQ3_M	3.76	15.6 GB	low
Q3_K_M	4	16.6 GB	low
Q3_K_L	4.3	17.8 GB	moderate
IQ4_XS	4.46	18.4 GB	moderate
Q4_K_S	4.67	19.3 GB	moderate
Q4_K_M	4.89	20.2 GB	good
Q5_K_S	5.57	22.9 GB	good
Q5_K_M	5.7	23.4 GB	good
Q6_K	6.56	26.9 GB	excellent
Q8_0	8.5	34.7 GB	lossless
FP16	16	64.9 GB	lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

Deploying for a team or in production? Size GPUs, cost & scaling in Enterprise →

▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN OLMO-2-0325-32B NOW

Rent on Vast.ai →Or RunPod →

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (15)

Arena Elo1222

MATH93.4

IFEval88.8

HumanEval86.7

BBH84.0

AIME77.3

AA Math77.3

LiveCodeBench69.5

MBPP65.1

alpacaeval59.8

GPQA Diamond53.9

GPQA48.6

AA Intelligence12.2

AA Coding5.6

HLE4.9

Run this model

▸Easiest way to get started·Beginners

DOCS ↗

curl -fsSL https://ollama.com/install.sh | sh

$ollama run olmo:32b-q4_K_M

Tag may need adjustment — check ollama.com/library/olmo for available tags.

▸ SETUP GUIDE

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more

Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

HuggingFace Ollama Library GGUF Downloads Build Hardware

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

NVIDIA RTX 4090

24 GB VRAM • 1008 GB/s

NVIDIA

$1599