DeepNetz

Chat Models Monitor Settings

Chat

No model loaded

DeepNetz

Load a model under Models to start chatting.

Temp 0.7

Tokens

Enter to send, Shift+Enter for new line

Loaded Model

Available Models

No local models found. Use CLI: deepnetz pull <model>

Model Hub

Loading model cards...

No model loaded

Inference Speed

0.0

tokens/sec

GPU Utilization

0%

No GPU detected

VRAM

0 / 0 GB

-- C

CPU Usage

0%

0 cores

RAM Usage

0 / 0 GB

0%

Tokens per Second (last 60s)

Inference Settings

Backend auto

GPU Layers 99

Context Length 4096

KV Cache Compression off

Generation Settings

Temperature 0.7

Top-P 0.9

Top-K 40

Repeat Penalty 1.1

Max Tokens 1024

Server Info

Status--

Model--

Backend--

GPU--

RAM--

OS--

DeepNetz — Open Source LLM Inference deepnetz.com GitHub