How can I help you today?
Powered by local Ollama AI models running directly on your server with high-speed streaming and long-term memory.
Model Playground & Prompt Lab
Tune generation parameters, test system prompts, and benchmark latency.
Parameters
Temperature
0.7
Deterministic (0.0)
Creative (2.0)
Top P
0.9
Execution Metrics
Duration:
-
Tokens Generated:
-
Speed:
-
Installed Models & Architecture
Manage models running inside the local Ollama daemon.
custom-assistant:latest
qwen2 / 494.03M
File Size:
0.37 GB
Quantization:
Q4_K_M
Format:
gguf
Context Length:
32768
qwen2.5:0.5b
qwen2 / 494.03M
File Size:
0.37 GB
Quantization:
Q4_K_M
Format:
gguf
Context Length:
32768
Host Environment & Services
Node.js Runtime
v20.19.2
Ollama Daemon
http://127.0.0.1:11434
Cloudflare Tunnel
Active Quick Tunnel