EbbotGPT LLMs

Read about the technical details and practical implications of Ebbot's LLMs.

GPT models

• EbbotGPT 2 - Released 12/12-2024

• EbbotGPT 0.6.4 - Released 23/5-2024

• EbbotGPT 3 Preview - Released 29/08-2025

EbbotGPT 3

Knowledge comprehension

EGPT3 has 3 times the parameters of EGPT2 which vastly improves its knowledge comprehension and problem-solving capabilities.

Speed

Despite being 3 times the size of EGPT2, EGPT3 is twice as fast because it uses a Mixture of Experts (MoE) architecture. This means the model only activates the most relevant 10% of its parameters to answer a user's query.

Integrated Tool Calling

EGPT3 features integrated tool calling, enabling it to seamlessly decide whether to use a tool or generate an answer from the uploaded knowledge.

Context Window

With a context window of 32,000 tokens, EGPT3 can process and manage four times more information than EGPT2.

EbbotGPT LLMs	Speed (1-10)	Knowledge (1-10)	Integrated tool calling	Context window (tokens)
2	6	7		8000
0.6.4	3	6		8000
3	8	9		32000