> ## Content Index
> Fetch the complete content index at: https://www.ai-360.online/llms.txt
> Use this file to discover other available public pages before exploring further.

# Jamba-1.5: Hybrid Transformer-Mamba Models at Scale
- URL: https://www.ai-360.online/ai21-labs-jamba-1-5-hybrid-transformer-mamba-models-at-scale/
- Published: 2024-08-22T12:00:00.000Z
- Updated: 2026-10-25T21:53:06.000Z
- Description: We present Jamba-1.5, new instruction-tuned large language models based on our Jamba architecture Jamba is a hybrid Transformer-Mamba mixture of experts…
- Author: Nicholas Lipinski
- Tags: news, #company-ai21-labs, 1. Enterprise AI

We present Jamba-1.5, new instruction-tuned large language models based on our Jamba architecture, [the company said on 22 August 2024](https://www.ai21.com/blog/jamba-1-5?ref=ai-360.online).

Jamba is a hybrid Transformer-Mamba mixture of experts architecture, providing high throughput and low memory usage across context lengths, while retaining the same or better quality as Transformer models. We release two model sizes: Jamba-1.5-Large, with 94B active parameters, and Jamba-1.5-Mini, with 12B active parameters. Both models are fine-tuned for a variety of conversational and instruction-following capabilities, and have an effective context length of 256K tokens, the largest amongst open-weight models.

Both models are fine-tuned for a variety of conversational and instruction-following capabilities, and have an effective context length of 256K tokens, the largest amongst open-weight models. To support cost-effective inference, we introduce ExpertsInt8, a novel quantization technique that allows fitting Jamba-1.5-Large on a machine with 8 80GB GPUs when processing 256K-token contexts without loss of quality.

For enterprise buyers, the useful next step is to map the claim to controls, data residency and measurable outcomes—and to ask for evidence on failure modes, oversight and auditability before treating the release as production-ready fact.

---