Cumulus LabsBack to Leaderboard
LLMs
Qwen 2.5 7B
+8.2%~$QW25-7
Fast 7B parameter LLM with strong instruction following. Optimized for high-throughput workloads where speed matters. Ideal for real-time agentic pipelines.
Deploy Now
#11 overall · 4 deploys
1.2s
Cold Start
avg on Ion
186ms
Avg Inference
per request
4
Active Replicas
right now
4
Total Deployments
all time
7-Day Trend
+8.2% this weekCold Start vs Competitors
Lower is better●~$QW25-71.2s
~$QW3-81.2s
~$QW301.7s
~$QW321.8s
Cold start comparison vs similar models. Lower is better.
Cost Estimate
Cost per 1K Inferences
$0.40
Est. Daily (1K req/day)
$0.40
Est. Monthly (30K req)
$12.00
No subscriptions. Buy credits, pay per inference. Scale to zero when idle.
Quick Deploy
cumulus-sdkimport cumulus from "cumulus-sdk" // Deploy Qwen 2.5 7B on Ion const client = await cumulus.deploy("qwen2-5-7b") // Run inference const result = await client.run({ prompt: "Your prompt here", // model-specific params... })