Llama 3 8B (Internal)
Llama 3 8B Instruct · dev-us-east-1 · RTX 4090 x2
addScale
P
Parthexpand_moreStatus
Running
Region
US-EAST
Uptime
88h
Req / hr
920
Cost / hr
$1.10
Deployment: Llama 3 8B (Internal)
Runninginput
Data Ingestion
Completedtune
Preprocessing
Completeddownload
Loading Model
Completedlocal_fire_department
Warming Up
Completedbolt
Serving
100%Serving Progress100%
Job Details
Job IDtrain_dep_04c9d
ModelLlama 3 8B Instruct
GPUs2 × RTX 4090
Start TimeMay 24, 2026 10:30 AM
Elapsed Time02:14:32
Est. Completion05:18:45 PM
Endpointhttps://api.spazenode.io/v1/dep_04
Real-time Monitoring
Active GPUs
2
±0% vs last 24h
GPU Utilization
21%
+3% vs last 24h
Memory Utilization
17%
+2% vs last 24h
Request Rate
920/hr
+7% vs last 24h
GPU Utilization Over Time
Last 24h21% average
GPU Memory Allocation
88%
VRAM
Model Weights
60%KV Cache
28%System Overhead
12%