Research

Jan-v3.5-4B

The first Jan personality — a 4B model fine-tuned for math reasoning with a distinct conversational identity.

Lightweight 4B code-tuned model for fast local coding assistance and agentic workflows.

4B parameter instruct model distilled from a larger teacher, optimized as a fine-tuning base.

8B vision-language model for long-horizon agentic automation in real software environments.

4B parameter model with strong performance on reasoning benchmarks.

Compact model with a 128k context window for long-document research and tool use.

Compact 32k-context model for fast local research and tool calling.