TextMath and reasoning

Tulu

Ai2 fine-tunes of Llama with a fully open recipe: data, code and all intermediate stages. Tulu 3 405B is one of the largest openly fine-tuned models; OLMo chat versions use the same recipe.

Developer
Ai2, USA
First release
Jun 2023
Latest release
Feb 2025
Sizes
7B – 405B
License
Commercial use with conditionsTulu 3: Llama 3.1 Community License; Tulu 2: Ai2 ImpACT Low-Risk; the first version was released as weight deltas to LLaMA 1
Russian
Not supported
Ready-made builds
GGUF
Running
Available in OllamaNeeds a GPU
Industries
Science and research, Customer support
Deploy on your server Hugging Face GitHub

What it does

  • Employee assistant on your own server
  • Math and precise instruction following
  • Reference recipe for your own fine-tuning

Where it is used

IT and R&DAnalyticsEducation

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
fits

Versions

  1. Tulu 3.1 8B
  2. Tulu 3 405B
  3. Tulu 3 (Llama 3.1 8B / 70B)
  4. Tulu 2 и Tulu 2 DPO (Llama 2, до 70B)
  5. Tulu (LLaMA, разница весов)

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 Tulu be used in a commercial project?

With conditions. License: Tulu 3: Llama 3.1 Community License; Tulu 2: Ai2 ImpACT Low-Risk; the first version was released as weight deltas to LLaMA 1. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does Tulu 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 Tulu support Russian?

No. The model card lists its languages and Russian is not among them.

Where can I download Tulu and what does it cost?

The Tulu 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

TextOLMoAllen 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.

DetailsTextLlamaMeta · USACommercial use with conditions

The models that started mass open source in AI. A huge ecosystem of fine-tuned versions and tools.

DetailsTextHermesNous Research · USACommercial use with conditions

Nous Research fine-tunes on top of Llama, Mistral, Qwen and Seed-OSS. Valued for precise instruction following, function calling and strict JSON output; they refuse less often than the originals; Hermes 4 has a reasoning mode.

Details

Source: huggingface.co/allenai/Llama-3.1-Tulu-3.1-8B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.