Specialized LLM for Core Banking.
Fine-Tuned
for InfoBasic & Java.
Standard public LLMs hallucinate on specialized banking code. TemenAI LLM is a domain-specific model fine-tuned on millions of lines of InfoBasic (jBC) and core banking Java schemas. Deploy locally, run offline, and keep all code proprietary.
100% On-Premise Privacy
No internet required. Run the model inside your secure DMZ or private network. Complete immunity from external data leaks and compliance risks.
InfoBasic & Java Expert
Trained to understand custom core banking logic. Deep comprehension of jBC routines, common blocks, standard routines, and T24 API calls.
Ultra-Low Latency
Optimized for local token generation. Connects seamlessly with Ollama, llama.cpp, or vLLM to deliver instant inline code completions in Eclipse.
Model Architectures & Sizing
Deploy the size that matches your enterprise GPU hardware infrastructure.
| Model Name | Base Architecture | Intelligence Score | Status |
|---|---|---|---|
| TemenAI-27B | Qwen3.6-27B | 46 | On Request |
| TemenAI-284B | DeepSeek-V4-Flash-284B | 51 | On Request |
Pre-Trained on Banking Syntaxes
Generic models struggle with proprietary legacy systems. We built the TemenAI LLM specifically to fill the knowledge gap in Temenos T24 customization, using strict data-cleansing pipelines to index core configurations.
- jBC (InfoBasic): Subroutines, validation routines, EB.API entries.
- Java Extensibility: TAFJ structure, component frameworks, L3 APIs.
- Metadata Formats: Enquiries, Versions, and SS definitions.
- Code Translation: Convert InfoBasic to modern Java.
Data-Center Deployments
Integrate easily with your existing orchestrators using standard open-source API standards.
Eclipse IDE
Developer environment with TemenAI Plugin. Captures cursor code context.
Secure Local Server
Ollama, vLLM, or Private API Gateway inside your banking DMZ.
TemenAI LLM
Weights loaded in local GPU. Analyzes context & streams completion.