USASI
Model release

Apriel-1.6-15B-Thinker

Release in the Apriel family · version Apriel-1.6-15b-Thinker

Maintained by ServiceNow (SLAM lab)13

A multimodal reasoning model of about 15B parameters that accepts text and images and writes its reasoning steps before a marked final answer. ServiceNow released it in December 2025 as an update to Apriel-1.5-15b-Thinker, with further continual pretraining, supervised fine-tuning, and reinforcement learning aimed partly at shorter reasoning.132

Last reviewedEntry updated Documented release Dec 9, 2025

Availability and license

Overall availability

Public

Downloadable from Hugging Face without gating.12

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

The license is stated as MIT in the model card's metadata and License section; the Hugging Face repository does not contain a separate LICENSE file.12

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-weight

The model parameters for this release can be downloaded by the public. License terms may still restrict use, redistribution, or commercial 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 Apriel-1.6-15B-Thinker
ItemStatusNotes and evidence
WeightsCan the general public download the model parameters for this release?PublicSafetensors weights are downloadable from Hugging Face; a GGUF conversion is published in a separate repository.126
Inference codeIs code for running the model published?PublicThe model card gives inference code for Hugging Face Transformers and a vLLM server command with Apriel tool-call and reasoning parsers.1
Training codeIs the code used to train the model published?PartialThe card names Fast-LLM and VERL as the training stack. Fast-LLM is ServiceNow's public training library (Apache 2.0), but this catalog did not find the Apriel-1.6 training configurations published.17
Training-data informationPublic = the training data itself can be obtained. Partial = composition or sources are documented without full access.PartialThe card and blog describe data categories (math, code, science, logical reasoning, multimodal image-text data, 2.4M SFT samples, synthetic data, and a share of NVIDIA Nemotron datasets in the upscaling mix). The training datasets themselves are not documented as released.13
Training recipeAre the training configuration and procedure documented in enough detail to follow?PartialThe card and blog outline the stages (depth-upscaling and continual pretraining, text then multimodal SFT, and multi-stage RL with GSPO) at a high level.13
Evaluation materialsPublic = evaluation code or prompts that let others re-run the evaluations are published. Partial = results only.PartialThe card publishes a results table; some text benchmark scores are taken from Artificial Analysis and the rest were evaluated internally. No evaluation code for this release was found.1

What it is useful for

The card lists code assistance and generation, logical and multi-step reasoning, question answering and information retrieval, function calling, complex instruction following, and agent use cases. It says the model is not intended for safety-critical applications without human oversight.1

Run and use notes

Documented facts only. No hardware or performance claims are made without a cited source and stated assumptions.
  • The model card documents inference with Hugging Face Transformers in bfloat16 and a vLLM OpenAI-compatible server with a 131,072-token maximum model length, and recommends a temperature of 0.6. It says the vLLM parsers were not yet merged upstream at the time and points to a custom Docker image.1
  • The card lists Together AI for hosted inference and Ollama for local use as additional options.1

Organization context

Provenance and derivatives

Apriel-1.6-15b-Thinker builds on ServiceNow's Apriel-1.5-15b-Thinker. The Apriel 1.5 report says that model started from Mistral AI's Pixtral-12B-Base-2409 (using a copy hosted by Unsloth), which ServiceNow depth-upscaled from 40 to 48 decoder layers before continued pretraining. The base weights were therefore not developed by ServiceNow.1345

Catalog records that name this entry in their provenance:

Other releases in the Apriel family

Apriel family overview

U.S. eligibility

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

Eligible · basis: U.S.-governed project

The model is published by ServiceNow's ServiceNow-AI organization on Hugging Face and described as part of ServiceNow's Apriel series. ServiceNow, Inc. is a Delaware corporation headquartered in Santa Clara, California, per its 2025 Form 10-K. The Apriel 1.5 line it builds on started from Pixtral-12B-Base-2409, published by Mistral AI; that base model is recorded under provenance and is not treated as U.S.-developed.184

Assessed Sep 29, 2026

Sources

  1. 1.
  2. 2.
  3. 3.
    Apriel-1.6-15b-Thinker: Cost-efficient Frontier Multimodal Performance (external site: huggingface.co)

    ServiceNow (Hugging Face blog) · Announcement · published Dec 9, 2025 · accessed Sep 29, 2026

  4. 4.
    Apriel-1.5-15b-Thinker (arXiv 2510.01141) (external site: arxiv.org)

    ServiceNow (SLAM Lab) · Paper · published Oct 1, 2025 · accessed Sep 29, 2026

  5. 5.
  6. 6.
    ServiceNow-AI on Hugging Face (external site: huggingface.co)

    ServiceNow (Hugging Face) · Repository · accessed Sep 29, 2026

  7. 7.
    ServiceNow/Fast-LLM (GitHub repository) (external site: github.com)

    ServiceNow · Repository · accessed Sep 29, 2026

  8. 8.
    ServiceNow, Inc. Form 10-K for the fiscal year ended December 31, 2025 (external site: sec.gov)

    U.S. Securities and Exchange Commission (ServiceNow filing) · Filing · published Jan 28, 2026 · 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