Cumulus LabsBack to Leaderboard
LLMs
Qwen 3 30B A3B
+16.4%~$QW30
Mixture-of-experts 30B model with only 3B active parameters per token. GPT-4o-level quality at a fraction of inference cost. Runs on all 5 universal-b nodes.
Deploy Now
#4 overall · 5 deploys
1.7s
Cold Start
avg on Ion
245ms
Avg Inference
per request
5
Active Replicas
right now
5
Total Deployments
all time
7-Day Trend
+16.4% this weekCold Start vs Competitors
Lower is better●~$QW301.7s
~$QW3-81.2s
~$QW321.8s
~$QW141.4s
Cold start comparison vs similar models. Lower is better.
Cost Estimate
Cost per 1K Inferences
$0.95
Est. Daily (1K req/day)
$0.95
Est. Monthly (30K req)
$28.50
No subscriptions. Buy credits, pay per inference. Scale to zero when idle.
Quick Deploy
cumulus-sdkimport cumulus from "cumulus-sdk" // Deploy Qwen 3 30B A3B on Ion const client = await cumulus.deploy("qwen3-30b-a3b") // Run inference const result = await client.run({ prompt: "Your prompt here", // model-specific params... })