DeepNetz

DN

DeepNetz

Load a model and start chatting.

Local Models

Registry

GPU

—

— VRAM · —

CPU

—

— cores

RAM

—

— / —

Inference

0 tok/s

Generation speed

Compute

Device

Context Length 4096

Generation

Temperature 0.7

Max Tokens

Top P 0.9

Backend

Backend

KV Compression

Advanced

Reasoning Mode

API Key

No model — — —