LLM
GA
Open weights
Jamba 1.6 Mini
Long context self-hosting with low memory
Release2025-03
Context256K
Max output—
Parameters52B
Local / VRAM48–80 GB
LicenseOpen weights
Overview
Jamba 1.6 Mini is a model in the LLM category from AI21 Labs. It was released in 2025-03. The vendor is based in Israel. Best for: Long context self-hosting with low memory.
Strengths
- 256K context
- Efficient
- Open weights
Limits
- No vision
- Previous generation
Specifications
| Vendor | AI21 Labs |
|---|---|
| Category | LLM |
| Release | 2025-03 |
| Status | GA |
| License | Open weights |
| License name | Jamba Open Model License |
| Commercial use | Allowed |
| Parameters | 52B |
| Active parameters | 12B |
| Architecture | hybrid Mamba-Transformer MoE |
| Context window | 256K |
| Input modalities | Text |
| Output modalities | Text |
| Prompt types | Text |
| Negative prompts | No |
| Max outputs | 1 |
| Local deployment | Yes |
| VRAM | 48–80 GB |
| System RAM | 64–128 GB |
| API access | Yes |
| Pricing | Free weights |
| Confidence | High |
| Vendor country | Israel |
| Vendor type | Frontier lab |
Pricing & hardware
Free weights
This model can be self-hosted or run locally. Approximate GPU memory: 48–80 GB. Approximate system RAM: 64–128 GB. API access is available.