Cumulus LabsBack to Leaderboard
LLMs
Qwen 2.5 32B
+11.3%~$QW32
High-capacity 32B language model. Best-in-class for complex instruction following, long-context tasks, and enterprise workflows. Runs on all 5 universal-b nodes.
Deploy Now
#7 overall · 5 deploys
1.8s
Cold Start
avg on Ion
420ms
Avg Inference
per request
5
Active Replicas
right now
5
Total Deployments
all time
7-Day Trend
+11.3% this weekCold Start vs Competitors
Lower is better●~$QW321.8s
~$QW3-81.2s
~$QW301.7s
~$QW141.4s
Cold start comparison vs similar models. Lower is better.
Cost Estimate
Cost per 1K Inferences
$1.60
Est. Daily (1K req/day)
$1.60
Est. Monthly (30K req)
$48.00
No subscriptions. Buy credits, pay per inference. Scale to zero when idle.
Quick Deploy
cumulus-sdkimport cumulus from "cumulus-sdk" // Deploy Qwen 2.5 32B on Ion const client = await cumulus.deploy("qwen2-5-32b") // Run inference const result = await client.run({ prompt: "Your prompt here", // model-specific params... })