TextMath and reasoningImage + text

Apriel

ServiceNow 15B models with step-by-step reasoning that fit on a single GPU. From version 1.5 they also understand images and are good at calling tools.

Developer
ServiceNow, USA
First release
Apr 2025
Latest release
Apr 2026
Sizes
5B – 15B
License
Commercial use allowedMIT
Russian
Not stated
Ready-made builds
GGUF
Running
On your own serverNeeds a GPU
Industries
Customer support, Software development, Documents and accounting
Deploy on your server Hugging Face GitHub

What it does

  • A reasoning assistant for internal services
  • Tool calling and enterprise agents
  • Analysing screenshots and documents with images

Where it is used

IT services and service deskCustomer supportDevelopment

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. SuperApriel-15B
  2. Apriel-1.6-15B-Thinker
  3. Apriel-1.5-15B-Thinker
  4. Apriel-Nemotron-15B-Thinker
  5. Apriel-5B

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can Apriel be used in a commercial project?

Yes. License: MIT. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Apriel need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Apriel support Russian?

The model card does not list languages, so Russian support cannot be promised — it has to be tested on your own examples.

Where can I download Apriel and what does it cost?

The Apriel weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

TextPhiMicrosoft · USACommercial use allowed

Small Microsoft models trained on carefully selected data: strong at logic and math for their modest size. Versions with images and speech are available.

DetailsTextNVIDIA NemotronNVIDIA · USACommercial use with conditions

NVIDIA models for agents and reasoning, optimized to run fast on its GPUs. Nemotron 3 is a Mamba and MoE hybrid from 4B to 550B; Nano Omni handles video, audio and images (English only).

DetailsTextIBM GraniteIBM · USACommercial use allowed

IBM enterprise models with transparent training data and ISO 42001 certification. Granite 4 is a memory-efficient Mamba and Transformer hybrid.

Details

Source: huggingface.co/ServiceNow-AI/SuperApriel-15B-Instruct. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.