CodeMath and reasoning

Rnj-1

An 8B model trained from scratch by the company of one of the authors of the transformer architecture. Strong at code and technical tasks; version 1.5 handles context up to 160K tokens.

Developer
Essential AI, USA
First release
Dec 2025
Latest release
Apr 2026
Sizes
8B
License
Commercial use allowedApache 2.0
Russian
Not stated
Ready-made builds
GGUF
Running
Available in OllamaNeeds a GPU
Industries
Software development, Science and research
Deploy on your server Hugging Face

What it does

  • Writing and fixing code
  • A developer agent on a single GPU
  • Solving technical and scientific problems

Where it is used

DevelopmentEngineering departmentsResearch

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. rnj-1.5-instruct
  2. rnj-1 и rnj-1-instruct

How to run it

With Ollama — the fastest wayInstall Ollama on your computer or server and find the model in its library by name. Good enough to try the model on your own tasks in one evening.Find it in the Ollama library
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 Rnj-1 be used in a commercial project?

Yes. License: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Rnj-1 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 Rnj-1 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 Rnj-1 and what does it cost?

The Rnj-1 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

CodeQwen CoderAlibaba (Qwen team) · ChinaCommercial use allowed

The broadest open coding family: from 0.5B for autocompletion to 480B for agents. Qwen3-Coder-Next (80B, 3B active) works as a developer agent on a single GPU.

DetailsCodeSeed-CoderByteDance Seed · ChinaCommercial use allowed

A compact 8B coding model from ByteDance in base, instruct and reasoning versions. Its training data was selected by the model itself, with almost no hand-written rules.

DetailsTextOLMoAllen Institute for AI (Ai2) · USACommercial use allowed

Fully open models: not only the weights but also the data, training code and intermediate checkpoints are published. Useful when transparent provenance matters.

Details

Source: huggingface.co/EssentialAI/rnj-1.5-instruct. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.