OLMo 3 32B Base
Parameters
32B
Context Length
66K
Modality
Text
Architecture
Dense
License
Apache 2.0
Release Date
25 Nov 2025
Knowledge Cutoff
Dec 2024
API Pricing (per 1M)
Input: $0.15 · Output: $0.50
System Requirements
VRAM requirements for different quantization methods and context sizes
1,024 tokens
Consumer
4x RTX 4090
24GB VRAM
Datacenter
1x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
65,536 tokens
Consumer
4x RTX 4090
24GB VRAM
Datacenter
2x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
Architecture Diagram
Evaluation Benchmarks
Rank
#146
| Benchmark | Score | Rank |
|---|---|---|
General Text | 1307 | 137 |
Intelligence Index | 0.07 | 207 |
Rankings
Overall Rank
#146
Coding Rank
-
About OLMo 3 32B Base
OLMo 3 32B Base is a 32B parameter open foundation model from Ai2 engineered for transparent NLP research, mathematical reasoning, and coding. It features hybrid sliding-window attention and YaRN RoPE scaling across a 65K context window.
Technical Specifications
Attention
Attention Structure
Multi-Head Attention
Attention Heads
40
Key-Value Heads
8
Attention Head Dimension
-
Position Embedding
Absolute Position Embedding
RoPE Theta
500,000
Sliding Window Attention
Yes
Sliding Window Size
4,096
Sliding Window Ratio
-
Linear Attention
-
Linear Attention Ratio
-
Normalization
RMS Normalization
Activation Function
SwigLU
Dimensions
Hidden Dimension Size
5,120
Number of Layers
64
FFN Intermediate Size (Dense)
27,648
Multi-Token Prediction Heads
-
Tokenizer
Vocabulary Size
100,278
About OLMo 3
OLMo (Open Language Model) is a series of fully open language models designed to enable the science of language models. Released by the Allen Institute for AI (Ai2), OLMo 3 provides complete access to training data (Dolma 3), code, checkpoints, logs, and evaluation methodologies. The family includes Base models for pretraining research, Instruct variants for chat and tool use, and Think variants with chain-of-thought reasoning capabilities. All models are trained with staged approach including pretraining, mid-training, and long-context phases.