Cumulus LabsBack to Leaderboard
LLMs
Qwen 3.5 27B
+24.2%~$QW3527
Dense Qwen 3.5 model with vision support and FP8 quantization. 128K context window with hybrid SSM attention. Exceptional long-document reasoning.
Deploy Now
#14 overall · 2 deploys
1.7s
Cold Start
avg on Ion
355ms
Avg Inference
per request
2
Active Replicas
right now
2
Total Deployments
all time
7-Day Trend
+24.2% this weekCold Start vs Competitors
Lower is better●~$QW35271.7s
~$QW3-81.2s
~$QW301.7s
~$QW321.8s
Cold start comparison vs similar models. Lower is better.
Cost Estimate
Cost per 1K Inferences
$1.20
Est. Daily (1K req/day)
$1.20
Est. Monthly (30K req)
$36.00
No subscriptions. Buy credits, pay per inference. Scale to zero when idle.
Quick Deploy
cumulus-sdkimport cumulus from "cumulus-sdk" // Deploy Qwen 3.5 27B on Ion const client = await cumulus.deploy("qwen3-5-27b") // Run inference const result = await client.run({ prompt: "Your prompt here", // model-specific params... })