It is speedy and making sense. Thanks much to agentica-org. 16-f already works very great on my edge computer. Please coach me if I make any mistake to convert it to gguf format.

Downloads last month
12
GGUF
Model size
1.78B params
Architecture
qwen2
Hardware compatibility
Log In to view the estimation

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for heylobc/DeepScaleR-1.5B-Preview-f16.gguf