rnj-1

Public

Rnj-1 is an 8B parameter open-weight, dense model trained from scratch by Essential AI, optimized for code and STEM with capabilities on par with SOTA open-weight models.

793 Downloads

1 star

Capabilities

Reasoning

Minimum system memory

6GB

Tags

8B
gemma3

README

rnj-1 by EssentialAI

rnj-1 is an 8B parameter open-weight, dense model trained from scratch by Essential AI, optimized for code and STEM with capabilities on par with SOTA open-weight models.

This model performs well across a range of programming languages and boasts strong agentic capabilities (e.g., inside agentic frameworks like mini-SWE-agent), while also excelling at tool-calling. It additionally exhibits strong capabilities in math and science.

Parameters

Custom configuration options included with this model

Reasoning Section Parsing
{ "enabled": true, "startString": "THOUGHT:", "endString": "RESPONSE:" }
Temperature
0.2
Top P Sampling
0.95

Sources

The underlying model files this model uses