Llama 3 8B (Internal)

Llama 3 8B Instruct · dev-us-east-1 · RTX 4090 x2

addScale
P
Parthexpand_more

Status

Running

Region

US-EAST

Uptime

88h

Req / hr

920

Cost / hr

$1.10

Deployment: Llama 3 8B (Internal)

Running
input

Data Ingestion

Completed
tune

Preprocessing

Completed
download

Loading Model

Completed
local_fire_department

Warming Up

Completed
bolt

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 24h

21% average

GPU Memory Allocation

88%

VRAM

Model Weights
60%
KV Cache
28%
System Overhead
12%