ModelLLMsvjamba-1.5-mini

Jamba 1.5 Mini

by AI21 Labs · open-source · Last verified 2026-03-17

AI21's compact hybrid SSM-Transformer model combining Mamba and attention layers for efficient long-context processing. Handles up to 256K tokens with significantly lower memory usage than pure transformer models of similar quality.

https://www.ai21.com/jamba ↗

C—Below Average

Adoption: C+Quality: B+Freshness: B+Citations: C+Engagement: F

Specifications

License: Jamba Open Model License
Pricing: open-source
Capabilities: text-generation, long-context, efficient-inference, reasoning, structured-output
Integrations: huggingface, langchain, aws-bedrock, azure-ai
Use Cases: long-document-analysis, summarization, enterprise-chatbots, research, data-extraction
API Available: Yes
Parameters: 52B (12B active)
Context Window: 256K tokens
Modalities: text
Training Cutoff: Mid 2024
Tags: llm, ssm, mamba, long-context, efficient
Added: 2026-03-17
Completeness: 100%

Index Score

49.35

Adoption

Quality

Freshness

Citations

Engagement

Explore the full AI ecosystem on Agents as a Service