🦙 Ollama Compatible API Server

Management Dashboard & Statistics

💬 Chat

Server Status

Status ONLINE
Device CUDA
Loaded Models 0
Total Models 1

GPU Information

CUDA Available YES
GPU Count 1
Memory Allocated 0.00 MB
Memory Reserved 0.00 MB

Request Statistics

allura-forge_Llama-3.3-8B-Instruct-Q5_K_M 1778 requests

Available Models

allura-forge_Llama-3.3-8B-Instruct-Q5_K_M UNLOADED
Size: 5.34 GB

Detailed Statistics

Model Requests Avg Response Time Total Input Tokens Total Output Tokens Success Rate
allura-forge_Llama-3.3-8B-Instruct-Q5_K_M 1778 4.767s 722040 151175 90.9%