Plain-English Summary
A more efficient Jamba model for enterprise workloads that need long context and controllable behavior.
Jamba2 Mini
A more efficient Jamba model for enterprise workloads that need long context and controllable behavior.
Jamba 2
General LLM
GA
Open weights: Model-dependent
API: Yes
Technical Notes
Hybrid Mamba-Transformer model with about 12B active parameters and 256K context.
Best For
Cost-efficient long-context RAG, extraction, enterprise assistants
Watch Out For
Lower capability than Jamba Large; total parameter count is not emphasized.
Model Specs
- Maker
- AI21 Labs
- Country
- Israel
- Family
- Jamba 2
- Type
- General LLM
- Release date
- Not listed
- Date confidence
- Not publicly stated
- Status
- GA
- Context window
- 262,144 tokens
- Max output
- Not listed
- Parameters
- Not disclosed
- Active parameters
- 12B
- Architecture
- Hybrid Mamba-Transformer
- Reasoning
- General reasoning
- Tool calling
- Yes
- Structured output
- Yes
- API available
- Yes
- Open weights
- Model-dependent
- Self-hostable
- Deployment dependent
- License
- Check model card
- Inputs
- Text
- Outputs
- Text
- Approx. price
- See provider pricing
- How to access
- Provider website or API
- Model / API ID
- jamba2-mini
- Knowledge cutoff
- Not publicly disclosed
- Fine-tuning
- Fine-tuning, private deployment, RAG
- Completeness
- 86 %
- Verified
- Jul 18, 2026
- Snapshot date
- Jul 18, 2026
- Source
- Official source