Text

Jamba

A hybrid of Transformer and Mamba with a window of up to 256K tokens: handles long documents faster than conventional models. Jamba2 focuses on accurate, source-based answers.

Developer
AI21 Labs, Israel
First release
Mar 2024
Latest release
Jan 2026
Sizes
3B – 398B-A94B
License
Commercial use with conditionsJamba v0.1, Reasoning 3B and Jamba2: Apache 2.0; Jamba 1.5–1.7: Jamba Open Model License with a revenue limit
Russian
Not supported
Ready-made builds
GGUF
Running
On your own serverAlso runs without a GPU
Industries
Legal, Customer support, Finance, Documents and accounting
Deploy on your server Hugging Face

What it does

  • Answers based on long policies and contracts
  • Knowledge-base search (RAG)
  • Summaries of large documents
  • Following strict instructions

Where it is used

Legal departmentsCustomer supportFinance

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. Jamba2 3B / Mini
  2. Jamba Reasoning 3B
  3. Jamba 1.7
  4. Jamba 1.6
  5. Jamba 1.5 Mini / Large
  6. Jamba v0.1

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 Jamba be used in a commercial project?

With conditions. License: Jamba v0.1, Reasoning 3B and Jamba2: Apache 2.0; Jamba 1.5–1.7: Jamba Open Model License with a revenue limit. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does Jamba 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 Jamba support Russian?

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

Where can I download Jamba and what does it cost?

The Jamba 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

TextFalconTechnology Innovation Institute (TII) · UAECommercial use with conditions

A family from Abu Dhabi: from the early Falcon 40B and 180B to hybrid Falcon-H1 and tiny Falcon-H1-Tiny models of 90–600M parameters for devices.

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.

DetailsTextCohere CommandCohere · CanadaCommercial use with conditions

Business models: document search with source citations, tool calling, many languages. Command A+ (2026) was the first under Apache 2.0, followed by the North line: code, translation and compact vision.

Details

Source: huggingface.co/ai21labs/AI21-Jamba2-Mini. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.