SAVRN
Search Contact SAVRN

Open-weight model · Text generation

OLMo-2-0425-1B

by Ai2 allenai/OLMo-2-0425-1B

We introduce OLMo 2 1B, the smallest model in the OLMo 2 family. OLMo 2 was pre-trained on OLMo-mix-1124 and uses Dolmino-mix-1124 for mid-training. OLMo 2 is the latest in a series of Open Language Models designed to enable the science of language models.

Parameters1.5B
Context4,096
Weights5.9 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads794k

Runs On

What it takes to serve OLMo-2-0425-1B (1.5B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso fits
16-bit 3.0 GB 3.6 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 1.5 GB 1.8 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 0.7 GB 0.9 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00

Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.

SAVRN's Notes on OLMo-2-0425-1B

Three gigabytes at 16-bit, 1.8 GB at 8-bit, under a gigabyte at 4-bit. Those figures decide where Ai2's 1.5-billion-parameter text model lives in a facility, and the answer is almost anywhere. The cheapest configuration in our data is one MI300X with 192 GB at $1.85 an hour, a card that could hold dozens of copies. We would run it beside a larger model rather than on its own hardware, and the 4,096-token context suits short prompts and short answers.

Apache 2.0 permits commercial use, modification and redistribution, asks you to keep the notices and state significant changes, and carries an express patent grant. The paper trail is the draw: Ai2 released code, checkpoints, logs and training details, naming OLMo-mix-1124 for pretraining and Dolmino-mix-1124 for mid-training. Check that your stack runs transformers 4.48 or later, and note the weights ship in float32, so the 5.9 GB on disk halves at 16-bit.

SAVRN Research, 2026-09-18

Model Card

By Ai2, published under apache-2.0, revision a1847dff3500.

Model Details

Model Card for OLMo 2 1B

We introduce OLMo 2 1B, the smallest model in the OLMo 2 family. OLMo 2 was pre-trained on OLMo-mix-1124 and uses Dolmino-mix-1124 for mid-training.

OLMo 2 is the latest in a series of Open Language Models designed to enable the science of language models. We have released all code, checkpoints, logs, and associated training details on GitHub.

Size Training Tokens Layers Hidden Size Attention Heads Context Length
OLMo 2-1B 4 Trillion 16 2048 16 4096
OLMo 2-7B 4 Trillion 32 4096 32 4096
OLMo 2-13B 5 Trillion 40 5120 40 4096
OLMo 2-32B 6 Trillion 64 5120 40 4096

The core models released in this batch include the following:

Read the full model card (1,045 words)

Configuration

Architecture
Olmo2ForCausalLM
Context length (tokens)
4,096
Layers
16
Hidden size
2,048
Feed-forward size
8,192
Attention heads
16
Key/value heads
16
Vocabulary size
100,352
RoPE base
500,000
Stored precision
float32
Model type
olmo2

Identity and Version

Repository
allenai/OLMo-2-0425-1B
Publisher
Ai2
Task
Text generation
Modality
Text
Library
transformers
Parameters
1.5B parameters
Languages
en
Revision
a1847dff35000b4271fa70afc5db10fd29fedbdf
First published
2025-04-17
Last updated
2025-05-28

Files and Weights

12 files, 5.9 GB in total. The weights are 2 files totalling 5.9 GB in safetensors.

Weights2 files · 5.9 GB
Configuration4 files · 15.7 KB
Tokenizer4 files · 9.7 MB
Documentation1 file · 12.9 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
model-00001-of-00002.safetensorsWeights5.0 GB c52e4ac8bf48
model-00002-of-00002.safetensorsWeights956.3 MB 5f80762572fe
config.jsonConfiguration623 B —
generation_config.jsonConfiguration121 B —
model.safetensors.index.jsonConfiguration14.9 KB —
special_tokens_map.jsonConfiguration125 B —
README.mdDocumentation12.9 KB —
.gitattributesRepository1.5 KB —
merges.txtTokenizer916.6 KB —
tokenizer.jsonTokenizer7.1 MB —
tokenizer_config.jsonTokenizer4.3 KB —
vocab.jsonTokenizer1.6 MB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
5.9 GB
Download from Ai2

Released by Ai2 through its official repository on Hugging Face. Read the license.

Built From

  • Described by arXiv:2501.00656

Memory Requirements

PrecisionWeights in memory
As published5.9 GB
16-bit3.0 GB
8-bit1.5 GB
4-bit0.7 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Compare OLMo-2-0425-1B

Questions About OLMo-2-0425-1B

How much GPU memory does OLMo-2-0425-1B need?

About 3.6 GB at 16-bit and 0.9 GB at 4-bit: the weights (1.5B parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run OLMo-2-0425-1B on?

At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

Can I use OLMo-2-0425-1B commercially?

Yes. OLMo-2-0425-1B is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

What is OLMo-2-0425-1B's context length?

4,096 tokens, from the maximum position embeddings in its published configuration.

Similar Models

Model · Text generation

Qwen2.5-1.5B-Instruct

Qwen

Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains. - Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and…

Open weights apache-2.0 1.5B parameters 32,768 tokens transformers
View model

Model · Text generation

Qwen2.5-1.5B

Qwen

Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains. - Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and…

Open weights apache-2.0 1.5B parameters 131,072 tokens transformers
View model

This repository contains an instruction-tuned causal language model for text generation and chat-style prompts. Use a recent version of transformers that supports this model architecture. The following example loads the model from this repository and generates a response.

Open weights apache-2.0 1.5B parameters 32,768 tokens transformers
View model

Model · Text generation

ia-vaga1.5B

Antonio V

This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

Open weights 1.5B parameters 32,768 tokens transformers
View model

A 1.2B hybrid model (SSM + attention) built in two stages: knowledge distillation from a 24B MoE hybrid teacher on STEM chain-of-thought data, then supervised fine-tuning on logical inference. The first proof-weighted distillation + SFT pipeline on a non-transformer architecture. Liquid Foundation Models run at 239 tok/s on AMD CPU and fit under 1GB of RAM. This model adds structured STEM reasoning and formal logical inference to that efficiency substrate. LFM2.5-1.2B distilled from LFM2-24B-A2B — a 24B MoE hybrid (SSM + attention) with only 2B active parameters per token. Teacher and student share the LFM hybrid architecture, so the KL divergence transfers reasoning patterns between…

Open weights apache-2.0 1.3B parameters 128,000 tokens transformers
View model