USASI
Model release

OpenELM 3B Instruct

Release in the OpenELM family · version OpenELM-3B-Instruct

Maintained by Apple31

OpenELM 3B Instruct is the 3B-parameter instruction-tuned model in Apple's April 2024 OpenELM release. It was pretrained with Apple's CoreNet library on about 1.8 trillion tokens of public data and then instruction-tuned on the UltraFeedback dataset using the Hugging Face Alignment Handbook.17

Last reviewedEntry updated Documented release Apr 2024

Availability and license

Overall availability

Public

Downloadable from Hugging Face without an access gate, under a license that permits only non-commercial research use.23

Availability is separate from permission: read the license before using or redistributing.

The weights license grants a personal, non-exclusive, revocable license to use, copy, modify, distribute, and create derivatives only for non-commercial scientific research, excluding product development and commercial use; derivatives are held to the same limit. Redistribution requires passing on the agreement with a specified attribution notice and identifying modifications. No patent rights are granted, and the agreement is governed by California law. The card's metadata uses the license tag "apple-amlr" but still gives "apple-sample-code-license" as the license name, while the LICENSE file in the repository (copyright 2025) is the research-only agreement. CoreNet's own license is a permissive Apple software license that grants no patent rights.324

Model-disclosure tier

Computed from the checklist below using USASI rubric v0.1. An editorial category, not a certification.
Model-disclosure tier (USASI rubric v0.1): Open-stack

Open-weight, plus published inference code, training code, and training recipe, and at least documented training-data composition.

The weights are under a license that is not on the rubric's OSI-approved list. Read its terms before use.

How tiers are computed

Public materials checklist

Items for a model under USASI rubric v0.1. Unknown means unassessed or insufficient evidence.
Public materials checklist for OpenELM 3B Instruct
ItemStatusNotes and evidence
WeightsCan the general public download the model parameters for this release?PublicWeights are published on Hugging Face without an access gate, under a research-only license.23
Inference codeIs code for running the model published?PublicThe Hugging Face repository includes model code and a generate_openelm.py script for inference with Transformers; CoreNet documents conversion to Apple's MLX.125
Training codeIs the code used to train the model published?PublicCoreNet documents OpenELM pre-training, and the instruction-tuning recipe uses the public Alignment Handbook with a configuration published in CoreNet.567
Training-data informationPublic = the training data itself can be obtained. Partial = composition or sources are documented without full access.PartialPre-training used public datasets (RefinedWeb, deduplicated PILE, a subset of RedPajama, and a subset of Dolma v1.6, about 1.8T tokens), and CoreNet documents where to download them and how the subsets were specified; instruction tuning used UltraFeedback. Current availability of each source dataset was not verified.167
Training recipeAre the training configuration and procedure documented in enough detail to follow?PublicApple published pre-training configurations and training logs, and the instruction-tuning README gives the recipe file and per-size hyperparameters.87
Evaluation materialsPublic = evaluation code or prompts that let others re-run the evaluations are published. Partial = results only.PublicThe model card gives the lm-evaluation-harness commit, tasks, and shot settings used to reproduce its reported zero-shot and few-shot results.1

What it is useful for

The card presents the model for open research on language models, notes it was trained on public data without safety guarantees, and asks users to do their own safety testing and filtering. Its license limits use to non-commercial research.13

Run and use notes

Documented facts only. No hardware or performance claims are made without a cited source and stated assumptions.
  • The card's evaluation commands load the model with trust_remote_code and pair it with the Llama 2 tokenizer (meta-llama/Llama-2-7b-hf); the CoreNet project notes that the models use the LLaMA v1/v2 tokenizer, which is downloaded separately.15

Organization context

Provenance and derivatives

Pretrained from scratch by Apple on public datasets using CoreNet, then instruction-tuned by Apple. The models use Meta's Llama tokenizer, which is not distributed with them.157

Other releases in the OpenELM family

No other releases in this family have been assessed.

OpenELM family overview

U.S. eligibility

Project eligibility rests on documented governing or maintaining entities, not on contributors.

Eligible · basis: U.S. headquarters

The model license states the model is developed and released by Apple Inc. Apple Inc. has its principal executive offices in Cupertino, California, per its Form 10-K for fiscal year 2025.39

Assessed Sep 29, 2026

Sources

  1. 1.
    apple/OpenELM-3B-Instruct model card (external site: huggingface.co)

    Apple (Hugging Face) · Model card · accessed Sep 29, 2026

  2. 2.
  3. 3.
  4. 4.
    apple/corenet LICENSE (external site: raw.githubusercontent.com)

    Apple Inc. (GitHub) · License · accessed Sep 29, 2026

  5. 5.
    CoreNet projects/openelm README (external site: raw.githubusercontent.com)

    Apple (GitHub) · Repository · accessed Sep 29, 2026

  6. 6.
  7. 7.
  8. 8.
  9. 9.
    Apple Inc. Form 10-K for the fiscal year ended September 27, 2025 (external site: sec.gov)

    Apple Inc. (via U.S. Securities and Exchange Commission EDGAR) · Filing · accessed Sep 29, 2026

This listing is not an endorsement, a safety assessment, or a federal approval.

Support Us

Help keep USASI useful.

Optional. No USASI account required. Payment takes place on the linked provider’s website (Buy Me a Coffee).

About supporting this project