Randomblock1/
nemotron-nano

7,193 6 months ago

Llama 3.1 customized by NVIDIA into a reasoning model that is post trained for reasoning, human chat preferences, and tasks, such as RAG and tool calling. Significantly improved performance over base Llama model.

tools thinking 8b

6 models

nemotron-nano:latest
470fceb39b43 • 4.9GB • 128K context window •
Text input • 6 months ago
nemotron-nano:8b latest
470fceb39b43 • 4.9GB • 128K context window •
Text input • 6 months ago
nemotron-nano:8b-instruct-q2_K
e7ae9fd52cf4 • 3.2GB • 128K context window •
Text input • 6 months ago
nemotron-nano:8b-instruct-q4_K_M
582787fbf6ee • 4.9GB • 128K context window •
Text input • 6 months ago
nemotron-nano:8b-instruct-q5_K_S
4de535b3249a • 5.6GB • 128K context window •
Text input • 6 months ago
nemotron-nano:8b-instruct-q6_K
18578fa5fc1f • 6.6GB • 128K context window •
Text input • 6 months ago