Math and reasoningTextFact-checking and judges

Limite (Violetto и Value Model)

A 1B model that does exactly one thing: it solves maths problems. It answers in a single turn, with no dialogue, and handles non-maths questions poorly. A companion Value Model scores someone else's solution step by step.

Developer
Paradigma, not disclosed
First release
Sep 2026
Latest release
Sep 2026
Sizes
1B
License
Commercial use allowedApache 2.0 for Violetto and the Value Model; the base builds have no license stated on their cards
Russian
Not stated
Running
On your own serverNeeds a GPU
Industries
Science and research, Education
Deploy on your server Hugging Face GitHub

What it does

  • Solving maths problems in a single answer
  • Picking the best solution out of several candidates
  • Scoring reasoning step by step when training another model
  • Checking calculations inside your own perimeter, without a cloud

Where it is used

EducationResearch groupsAI development

Hardware requirements

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

Versions

  1. Limite 1B Value Model
  2. Limite 1B Violetto
  3. Limite 1B base

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.

Frequently asked questions

Can Limite (Violetto и Value Model) be used in a commercial project?

Yes. License: Apache 2.0 for Violetto and the Value Model; the base builds have no license stated on their cards. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Limite (Violetto и Value Model) need?

At minimum: One GPU with 16–80 GB — mid-size 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 Limite (Violetto и Value Model) 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 Limite (Violetto и Value Model) and what does it cost?

The Limite (Violetto и Value Model) 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

Math and reasoningDeepSeek-MathDeepSeek · ChinaCommercial use with conditions

DeepSeek's maths models. The first 7B version introduced the GRPO training method; the 685B V2 writes and checks its own olympiad-level proofs.

DetailsMath and reasoningQwen2.5-MathQwen (Alibaba) · ChinaCommercial use with conditions

Maths versions of Qwen: they solve problems step by step and can calculate via code. Includes reward models that check each step of a solution.

DetailsMath and reasoningGoedel-ProverPrinceton University · USACommercial use allowed

Open models for formal proofs in Lean 4 from Princeton. The new Goedel-Code-Prover proves program correctness.

Details

Source: huggingface.co/api/models?author=paradigma-inc. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.