Jamba
Hybrid SSM-Transformer model by AI21 Labs combining Mamba with attention layers.
Open SourceSelf HostedOffline CapableGPU Required (12GB+ VRAM)
0.0 (0)
About
Jamba by AI21 Labs is a hybrid architecture combining Mamba state-space layers with Transformer attention layers and MoE. Achieves strong performance with 256K context and efficient inference. Available in 1.5-Mini (12B active). Apache 2.0 license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- Large Language Models (LLMs)
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Intermediate (3/5)
- License
- Apache-2.0
- Minimum VRAM
- 12 GB
- Added
- Apr 3, 2026
Similar Tools
Featured
Open-weight LLM by Meta available in 8B, 70B, and 405B parameter sizes.
Open SourceSelf HostedOfflineGPU 8GB+
Intermediate
0.0 (0)
Featured
Latest Llama model family by Meta with Mixture-of-Experts architecture.
Open SourceSelf HostedOfflineGPU 16GB+
Advanced
0.0 (0)
Featured
High-performance open-weight LLMs by Mistral AI with MoE architecture.
Open SourceSelf HostedOfflineGPU 8GB+
Intermediate
0.0 (0)