---
title: "Ai2 models: release history and timeline"
description: "The Allen Institute for AI is a nonprofit research institute that releases fully open models such as OLMo, OLMoE, Tülu and Molmo together with their training data, code and checkpoints."
type: "release-archive"
canonical_url: "https://theaiengineering.com/releases/ai2"
markdown_url: "https://theaiengineering.com/releases/ai2.md"
author: "The AI Engineering Editors"
publisher: "The AI Engineering"
updated: "2026-10-02"
citation: "The AI Engineering Editors. \"Ai2 models: release history and timeline.\" The AI Engineering, updated Oct 02, 2026. https://theaiengineering.com/releases/ai2"
license: "CC BY 4.0"
license_url: "https://creativecommons.org/licenses/by/4.0/"
data_csv: "https://theaiengineering.com/releases.csv"
data_json: "https://theaiengineering.com/releases.json"
---

# Ai2 models: release history and timeline

The Allen Institute for AI is a nonprofit research institute that releases fully open models such as OLMo, OLMoE, Tülu and Molmo together with their training data, code and checkpoints.

- Headquarters: Seattle, United States
- Founded: 2014
- Website: https://allenai.org

23 releases from 1 lab, 23 with open weights. Dates are the labs' official announcement dates.

## October 2026

### AstaBrief 8B

Open-weights model that turns a research question and retrieved literature excerpts into a cited scientific report, powering Fast mode in Asta's report generation.

- Date: 2026-10-02
- Lab: Ai2
- Type: LLM
- Weights: Open weights
- Modalities: text → text
- Parameters: 8B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2026/10#astabrief

Highlights:

- Post-trained from Qwen3-8B
- Training data open-sourced with the model
- Released under Apache 2.0

Source: [Open-sourcing AstaBrief, the fast report-generation model in Asta | Ai2](https://allenai.org/blog/astabrief)

## May 2026

### EMO

Research mixture-of-experts model pretrained so that modular structure emerges from data, letting a task use about 12.5% of its experts with near full performance.

- Date: 2026-05-08
- Lab: Ai2
- Type: LLM
- Weights: Open weights
- Modalities: text → text
- Parameters: MoE: 14B total, 1B active
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2026/05#emo

Highlights:

- 128 experts in total with 8 active
- Trained on 1 trillion tokens
- Released under Apache 2.0

Source: [EMO: Pretraining mixture of experts for emergent modularity | Ai2](https://allenai.org/blog/emo)

### MolmoAct 2

Upgrade to Ai2's Action Reasoning Model that pairs the Molmo 2-ER embodied reasoning model with a flow-matching action expert for real-world robots.

- Date: 2026-05-05
- Lab: Ai2
- Type: Multimodal
- Weights: Open weights
- Modalities: text, image → action
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2026/05#molmoact-2

Highlights:

- Molmo 2-ER released as the reasoning backbone
- Includes an open action tokenizer
- Full code and training data released later

Source: [MolmoAct 2: An open foundation for robots that work in the real world | Ai2](https://allenai.org/blog/molmoact2)

## March 2026

### MolmoWeb

Open visual web agent built on Molmo 2 that navigates websites, fills out forms and retrieves information in a browser, designed for self-hosting.

- Date: 2026-03-24
- Lab: Ai2
- Type: Multimodal
- Weights: Open weights
- Modalities: text, image → text
- Parameters: 4B and 8B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2026/03#molmoweb

Highlights:

- Released with weights, training data and evaluation tools
- Training data includes 36K human task trajectories
- Released under Apache 2.0

Source: [MolmoWeb: An open agent for automating web tasks | Ai2](https://allenai.org/blog/molmoweb)

### Olmo Hybrid

Fully open 7B model family that mixes transformer attention with linear recurrent layers, released with a controlled comparison against Olmo 3 7B.

- Date: 2026-03-05
- Lab: Ai2
- Type: LLM
- Weights: Open weights
- Modalities: text → text
- Parameters: 7B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2026/03#olmo-hybrid

Highlights:

- Combines transformers and linear RNNs
- Developed through 1B and 7B scale experiments
- Released under Apache 2.0

Source: [Introducing Olmo Hybrid: Combining transformers and linear RNNs for superior scaling | Ai2](https://allenai.org/blog/olmohybrid)

## January 2026

### SERA

First release in Ai2's Open Coding Agents family, coding models built on Qwen 3 with a training method for adapting agents to any repository.

- Date: 2026-01-27
- Lab: Ai2
- Type: Coding
- Weights: Open weights
- Modalities: text → text
- Parameters: 8B to 32B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2026/01#sera

Highlights:

- Trained up to 32K context length
- SERA-14B added on February 3, 2026
- Released under Apache 2.0

Source: [Open Coding Agents: Fast, accessible coding agents that adapt to any repo | Ai2](https://allenai.org/blog/open-coding-agents)

## December 2025

### Bolmo

Family of byte-level language models created by byteifying Olmo 3 models, reusing their backbones while replacing subword tokenization with byte-level patching.

- Date: 2025-12-15
- Lab: Ai2
- Type: LLM
- Weights: Open weights
- Modalities: text → text
- Parameters: 1B and 7B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/12#bolmo

Highlights:

- Uses an mLSTM local encoder and a boundary predictor
- Built on the public Olmo 3 7B checkpoint
- Released under Apache 2.0

Source: [Introducing Bolmo: Byteifying the next generation of language models | Ai2](https://allenai.org/blog/bolmo)

### Olmo 3.1

Update to Olmo 3 with two new 32B checkpoints, Olmo 3.1 Think 32B and Olmo 3.1 Instruct 32B, plus refreshed RL Zero 7B models.

- Date: 2025-12-12
- Lab: Ai2
- Type: Reasoning
- Weights: Open weights
- Modalities: text → text
- Parameters: 32B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/12#olmo-3-1

Highlights:

- Think 32B came from 21 more days of RL training on 224 GPUs
- Instruct 32B applies the Olmo 3 Instruct 7B recipe at larger scale
- Released under Apache 2.0

Source: [Olmo 3: Charting a path through the model flow to lead open-source AI | Ai2](https://allenai.org/blog/olmo3)

### Molmo 2

Successor to Ai2's Molmo that extends its grounded vision capabilities to video and multi-image understanding, adding video pointing and tracking, released with open weights.

- Date: 2025-12-11
- Lab: Ai2
- Type: Multimodal
- Weights: Open weights
- Modalities: text, image, video → text
- Parameters: 4B, 7B and 8B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/12#molmo-2

Highlights:

- Molmo 2 8B and 4B are built on Qwen 3
- Molmo 2-O 7B is built on Olmo for a fully open stack
- Full training codebase released later

Source: [Molmo 2: State-of-the-art video understanding, pointing, and tracking | Ai2](https://allenai.org/blog/molmo2)

## November 2025

### Olmo 3

Third generation of fully open Olmo models, released as Base, Think, Instruct and RL Zero variants with checkpoints from every major stage of training.

- Date: 2025-11-20
- Lab: Ai2
- Type: Reasoning
- Weights: Open weights
- Modalities: text → text
- Parameters: 7B and 32B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/11#olmo-3

Highlights:

- Pretrained on the new Dolma 3 data
- Releases base, mid-trained, long-context and post-training checkpoints
- Released under Apache 2.0

Source: [Olmo 3: Charting a path through the model flow to lead open-source AI | Ai2](https://allenai.org/blog/olmo3)

## October 2025

### olmOCR 2

Updated OCR model for English digitized print documents, built on Qwen2.5-VL-7B and trained with unit test rewards for document correctness.

- Date: 2025-10-22
- Lab: Ai2
- Type: Multimodal
- Weights: Open weights
- Modalities: text, image → text
- Parameters: 7B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/10#olmocr-2

Highlights:

- Released as olmOCR-2-7B-1025
- Fine-tuned on olmOCR-mix-1025 with 270,000 PDF pages
- Released under Apache 2.0

Source: [olmOCR 2: Unit test rewards for document OCR | Ai2](https://allenai.org/blog/olmocr-2)

## August 2025

### OLMoASR

Family of fully open English automatic speech recognition models from Ai2, trained from scratch on a curated, large-scale dataset and released in sizes from 244M to 1.5B.

- Date: 2025-08-28
- Lab: Ai2
- Type: Speech
- Weights: Open weights
- Modalities: audio → text
- Parameters: 244M to 1.5B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/08#olmoasr

Highlights:

- Sizes include small.en at 244M, medium.en at 769M and two 1.5B large.en models
- The large.en-v2 model was trained on 680,000 hours of audio
- Released under Apache 2.0

Source: [OLMoASR: A series of open speech recognition models | Ai2](https://allenai.org/blog/olmoasr)

### MolmoAct

Ai2's first Action Reasoning Model, a robotics model that reasons about its environment in 3D before acting, released with an open post-training dataset.

- Date: 2025-08-12
- Lab: Ai2
- Type: Multimodal
- Weights: Open weights
- Modalities: text, image → action
- Parameters: 7B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/08#molmoact

Highlights:

- Post-trained on about 10,000 distinct robot episodes
- Pretrained on a curated subset of Open-X Embodiment data
- Released under Apache 2.0

Source: [MolmoAct: An Action Reasoning Model that reasons in 3D space | Ai2](https://allenai.org/blog/molmoact)

## July 2025

### FlexOlmo

Language model training paradigm in which each data owner branches from a shared public model and trains an expert locally on its own data, letting owners opt in or out later.

- Date: 2025-07-09
- Lab: Ai2
- Type: LLM
- Weights: Open weights
- Modalities: text → text
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/07#flexolmo

Highlights:

- Enables collaboration without pooling sensitive data
- Released as FlexOlmo-7x7B-1T on Hugging Face
- Released under Apache 2.0

Source: [Introducing FlexOlmo: a new paradigm for language model training and data collaboration | Ai2](https://allenai.org/blog/flexolmo)

## March 2025

### OLMo 2 32B

Largest model in the OLMo 2 family and a fully open model trained on up to 6 trillion tokens and post-trained with Tülu 3.1.

- Date: 2025-03-13
- Lab: Ai2
- Type: LLM
- Weights: Open weights
- Modalities: text → text
- Parameters: 32B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/03#olmo-2-32b

Highlights:

- Trained with the new OLMo-core codebase
- Trained on Google Cloud's Augusta AI Hypercomputer
- Released under Apache 2.0

Source: [OLMo 2 32B: First fully open model to outperform GPT 3.5 and GPT 4o mini | Ai2](https://allenai.org/blog/olmo2-32b)

## February 2025

### olmOCR

Open PDF text extraction toolkit built on a fine-tuned Qwen2-VL-7B-Instruct model, released with weights, fine-tuning data and an efficient inference pipeline.

- Date: 2025-02-25
- Lab: Ai2
- Type: Multimodal
- Weights: Open weights
- Modalities: text, image → text
- Parameters: 7B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/02#olmocr

Highlights:

- Built on Qwen2-VL-7B-Instruct
- Released with training and inference code
- Followed by olmOCR 2 in October 2025

Source: [olmOCR: Efficient PDF text extraction with vision language models | Ai2](https://allenai.org/blog/olmocr)

## January 2025

### Tülu 3 405B

Application of the fully open Tülu 3 post-training recipe to the Llama 3.1 405B base model, used to stress-test reinforcement learning with verifiable rewards at scale.

- Date: 2025-01-30
- Lab: Ai2
- Type: LLM
- Weights: Open weights
- Modalities: text → text
- Parameters: 405B
- License: Llama 3.1 Community License
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/01#tulu-3-405b

Highlights:

- Trained with reinforcement learning from verifiable rewards
- Served with vLLM using 16-way tensor parallelism during RL
- Built on Llama 3.1 405B

Source: [Scaling the Tülu 3 post-training recipes to surpass the performance of DeepSeek V3 | Ai2](https://allenai.org/blog/tulu-3-405b)

## November 2024

### OLMo 2

Second generation of fully open OLMo models, trained on up to 5 trillion tokens and released with weights, data, code, recipes, checkpoints and instruct versions.

- Date: 2024-11-26
- Lab: Ai2
- Type: LLM
- Weights: Open weights
- Modalities: text → text
- Parameters: 7B and 13B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2024/11#olmo-2

Highlights:

- Released in 7B and 13B sizes
- OLMo 2-Instruct models apply the Tülu 3 post-training recipe
- Released under Apache 2.0

Source: [OLMo 2: The best fully open language model to date | Ai2](https://allenai.org/blog/olmo2)

### Tülu 3

Family of post-trained Llama 3.1 models released with all of their data, data mixes, recipes, code, infrastructure and evaluation framework.

- Date: 2024-11-21
- Lab: Ai2
- Type: LLM
- Weights: Open weights
- Modalities: text → text
- Parameters: 8B and 70B
- License: Llama 3.1 Community License
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2024/11#tulu-3

Highlights:

- Opens up the full post-training recipe
- Built on Llama 3.1 base models
- Later scaled to 405B parameters

Source: [Tülu 3 opens language model post-training up to more tasks and more people | Ai2](https://allenai.org/blog/tulu-3)

## September 2024

### Molmo

Family of open vision-language models trained without distillation from proprietary VLMs, notable for learning to point at what they perceive in images.

- Date: 2024-09-25
- Lab: Ai2
- Type: Multimodal
- Weights: Open weights
- Modalities: text, image → text
- Parameters: 1B (MolmoE), 7B and 72B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2024/09#molmo

Highlights:

- Weights, captioning data and fine-tuning data released
- Released as MolmoE-1B, Molmo-7B-O, Molmo-7B-D and Molmo-72B
- Built from pretrained vision encoders and language-only LLMs

Source: [Molmo | Ai2](https://allenai.org/blog/molmo)

### OLMoE

First mixture-of-experts model in the OLMo family, developed with Contextual AI and released with open data, code, logs and intermediate checkpoints.

- Date: 2024-09-04
- Lab: Ai2
- Type: LLM
- Weights: Open weights
- Modalities: text → text
- Parameters: MoE: 7B total, 1B active
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2024/09#olmoe

Highlights:

- Trained on 5 trillion tokens
- 244 pretraining checkpoints released, one every 5,000 steps
- Instruct version previewed the Tülu 3 post-training pipeline

Source: [OLMoE: An open, small, and state-of-the-art mixture-of-experts model | Ai2](https://allenai.org/blog/olmoe-an-open-small-and-state-of-the-art-mixture-of-experts-model-c258432d0514)

## April 2024

### OLMo 1.7 7B

Updated 7B OLMo model with a longer context window, a new two-stage training procedure and improved data, released with the Dolma 1.7 dataset.

- Date: 2024-04-17
- Lab: Ai2
- Type: LLM
- Weights: Open weights
- Modalities: text → text
- Context window: 4,096 tokens
- Parameters: 7B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2024/04#olmo-1-7

Highlights:

- Context length raised from 2,048 to 4,096 tokens
- Trained on the new Dolma 1.7 data mix
- Released under Apache 2.0

Source: [OLMo 1.7–7B: A 24 point improvement on MMLU | Ai2](https://allenai.org/blog/olmo-1-7-7b-a-24-point-improvement-on-mmlu-92b43f7d269d)

## February 2024

### OLMo

Ai2's first truly open language model, released with its full pretraining data, training code, model weights and evaluation tools so researchers can study how it was built.

- Date: 2024-02-01
- Lab: Ai2
- Type: LLM
- Weights: Open weights
- Modalities: text → text
- Context window: 2,048 tokens
- Parameters: 1B and 7B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2024/02#olmo

Highlights:

- Pretrained on the open Dolma corpus of about three trillion tokens
- Built with partners including the Kempner Institute, AMD and the LUMI supercomputer
- Available on Hugging Face and GitHub

Source: [Hello OLMo: A truly open LLM | Ai2](https://allenai.org/blog/hello-olmo-a-truly-open-llm-43f7e7359222)

## Cite and reuse this data

These release records are free to reuse under CC BY 4.0, including commercially. Credit The AI Engineering and link to this page's URL. Dates are the labs' official announcement dates, and every record links to its source. List fields in the CSV are separated by " | ".

The AI Engineering Editors. "Ai2 models: release history and timeline." The AI Engineering, updated Oct 02, 2026. https://theaiengineering.com/releases/ai2

HTML link:

```html
<a href="https://theaiengineering.com/releases/ai2">Ai2 models: release history and timeline</a> (The AI Engineering)
```

- Title: Ai2 models: release history and timeline
- Author: The AI Engineering Editors
- Publisher: The AI Engineering
- Updated: 2026-10-02
- URL: https://theaiengineering.com/releases/ai2
- Markdown: https://theaiengineering.com/releases/ai2.md
- License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)
- Full dataset as CSV: https://theaiengineering.com/releases.csv
- Full dataset as JSON: https://theaiengineering.com/releases.json
