Ollama Herd
Dashboard
Trends
Model Insights
Tags
Benchmarks
Health
Recommendations
Settings
▶ Run Benchmark
Capacity Growth
Throughput Trend
Model Throughput
(latest run)
Model Latency
(latest run)
Model Performance Over Time
Node Utilization
(latest run)
Date
Duration
Nodes
Models
Requests
Tok/s
Latency p50
TTFT p50
No benchmark runs yet
Run your first benchmark:
python scripts/benchmark.py --duration 60