Project AURIONAI Use-Cases Research & Innovation
LLM

Jamba 1.5 Large

AI21 Labs open long-context model on the hybrid SSM-Transformer Jamba architecture with a 256K context window, aimed at enterprise document and RAG workloads.

AI21 LabsAI21 LabsIsraelJamba 1.5Family
AI21 Labs
Levelmodel
ClassLLM
Parametersnot in the notes
Context256,000
Released22 Aug 2024
Opennessopen weights restricted
Runs onmulti-GPU node
Statusactive

R&D Topics

Efficiency architectures (MoE, sparse attention, long context)produced by

Identity

Developer
AI21 Labs
Family
Jamba 1.5
Released
22 Aug 2024 sourcesannouncement page
Weights published
22 Aug 2024
Record checked
11 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
hybrid SSM-Transformer (Mamba plus Transformer) with MoE layers
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Context length
256,000 tokens
Input
text
Output
text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
open weights restricted
Licence
Jamba Open Model License Agreement sources
Access routes
API, cloud marketplace, open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
multi-GPU node
Footprint
Cannot be loaded in FP32 or BF16 on a single node of 8 GPUs; AI21 ExpertsInt8 quantization lets it fit on one 8-GPU node
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
English, Spanish, French, Portuguese, Italian, Dutch, German, Arabic, Hebrew
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Lineage

The notes record no lineage for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. ai21.com/blog/announcing-jamba-model-family https://www.ai21.com/blog/announcing-jamba-model-family/
  2. ai21.com/jamba-open-model-license https://www.ai21.com/jamba-open-model-license

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Jamba 1.5 Large", https://aurion.semai.id/models/ai21-labs-jamba-1-5-large/, records of October 2026.