TextCode

StableLM и Stable Code

Small models from Stability AI: StableLM 2 (1.6B) knows 7 European languages, Stable Code (3B) completes code. No updates since 2024.

The last open version came out in Aug 2024. The family has not been updated for a long time: the model still works, but do not expect fixes or new sizes.

Developer
Stability AI, UK
First release
Apr 2023
Latest release
Aug 2024
Sizes
1.6B – 12B
License
Commercial use with conditionsEarly Alpha and StableLM-3B-4E1T: CC BY-SA 4.0; StableLM 2 1.6B, Zephyr and Stable Code: Stability AI Community License (free for revenue up to 1 million dollars a year); StableLM 2 12B: non-commercial
Russian
Not supported
Ready-made builds
GGUF
Running
Available in OllamaAlso runs without a GPU
Industries
Customer support, Software development, Education
Deploy on your server Hugging Face GitHub

What it does

  • A lightweight chatbot on an ordinary PC
  • Code autocompletion in the editor
  • A base for fine-tuning on your own task

Where it is used

DevelopmentCustomer supportEducation

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. Arabic StableLM 2
  2. StableLM 2 12B
  3. Stable Code Instruct 3B
  4. StableLM 2 1.6B и Stable Code 3B
  5. StableLM Zephyr 3B
  6. StableLM-3B-4E1T
  7. StableLM Alpha (3B, 7B)

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 StableLM и Stable Code be used in a commercial project?

With conditions. License: Early Alpha and StableLM-3B-4E1T: CC BY-SA 4.0; StableLM 2 1.6B, Zephyr and Stable Code: Stability AI Community License (free for revenue up to 1 million dollars a year); StableLM 2 12B: non-commercial. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does StableLM и Stable Code need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does StableLM и Stable Code support Russian?

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

Where can I download StableLM и Stable Code and what does it cost?

The StableLM и Stable Code 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

TextSmolLMHugging Face · USACommercial use allowed

Tiny open Hugging Face models for phones and laptops. SmolLM3 (3B) can reason and handle long context; the full training recipe is open.

DetailsTextPhiMicrosoft · 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.

DetailsCodeStarCoderBigCode (Hugging Face and ServiceNow) · USA / FranceCommercial use with conditions

One of the first open coding models, trained on an open set of source code with an option to exclude your own repository. Today it is more a base for fine-tuning than a leader.

Details

Source: huggingface.co/stabilityai/stablelm-2-12b-chat. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.