🖥️ AI Server Fleet Control Panel

🖥️
5
Active Servers
🎮
12
Active GPUs
🤖
8
Running Models
📊
15
Queued Jobs
⚡
450
Tokens/Second
🔌
1.2 kW
Power Usage

📈 Token Generation Rate

270 t/s
337 t/s
360 t/s
292 t/s
315 t/s

📋 Activity Log

[10:23:45]Server hermes-01: Model Qwen3.6 27B MTP started inference job #1234

[10:23:42]Server hermes-02: GPU 0 temperature at 65°C, VRAM usage 14.2GB

[10:23:38]Server hermes-03: GPU 1 temperature approaching threshold (68°C)

[10:23:35]Server hermes-04: Job #1233 completed successfully

[10:23:30]Server hermes-05: Model Qwen3.6 27B MTP loaded into memory

🖥️ hermes-01

Status Running
CPU 45%
RAM 64GB / 128GB
Disk 120GB / 500GB
Network 1.2 Gbps
Uptime 7d 12h
Models Qwen3.6 27B MTP

🖥️ hermes-02

Status Running
CPU 38%
RAM 96GB / 128GB
Disk 80GB / 500GB
Network 0.8 Gbps
Uptime 5d 8h
Models Qwen3.6 27B MTP, Qwen Coder

🖥️ hermes-03

Status Running
CPU 52%
RAM 80GB / 128GB
Disk 200GB / 500GB
Network 1.5 Gbps
Uptime 3d 4h
Models Qwen3.6 27B MTP

🖥️ hermes-04

Status Running
CPU 41%
RAM 72GB / 128GB
Disk 150GB / 500GB
Network 1.0 Gbps
Uptime 9d 16h
Models Qwen3.6 27B MTP

🖥️ hermes-05

Status Running
CPU 47%
RAM 88GB / 128GB
Disk 95GB / 500GB
Network 1.3 Gbps
Uptime 4d 6h
Models Qwen3.6 27B MTP

🎮 GPU Monitor

🖥️ hermes-01 GPU 0
VRAM
14.2 GB / 16 GB
Temp
65°C
Fan
45%
Power
180W
t/s
270
Load
89%
🖥️ hermes-01 GPU 1
VRAM
12.8 GB / 16 GB
Temp
58°C
Fan
40%
Power
165W
t/s
245
Load
80%
🖥️ hermes-02 GPU 0
VRAM
15.1 GB / 16 GB
Temp
70°C
Fan
50%
Power
195W
t/s
295
Load
94%
🖥️ hermes-03 GPU 0
VRAM
13.5 GB / 16 GB
Temp
62°C
Fan
42%
Power
172W
t/s
260
Load
84%
🖥️ hermes-04 GPU 0
VRAM
14.8 GB / 16 GB
Temp
68°C
Fan
48%
Power
188W
t/s
278
Load
92%
🖥️ hermes-05 GPU 0
VRAM
13.2 GB / 16 GB
Temp
60°C
Fan
38%
Power
158W
t/s
235
Load
82%

🤖 Model Deployment Table

Model Name Quantization Context GPU Status Jobs
Qwen3.6 27B MTP MTP 4-bit 32K hermes-01 GPU 0 Running 3
Qwen3.6 27B MTP MTP 4-bit 32K hermes-02 GPU 0 Running 2
Qwen3.6 27B MTP MTP 4-bit 32K hermes-03 GPU 0 Running 1
Qwen3.6 27B MTP MTP 4-bit 32K hermes-04 GPU 0 Running 4
Qwen3.6 27B MTP MTP 4-bit 32K hermes-05 GPU 0 Running 2
Qwen Coder MTP 4-bit 16K hermes-02 GPU 1 Running 1
Qwen3.6 27B MTP MTP 4-bit 32K hermes-02 GPU 1 Paused 0
Qwen3.6 27B MTP MTP 4-bit 32K hermes-03 GPU 1 Error 0

📋 Inference Queue

Job #1234
Active
Qwen3.6 27B MTP
Job #1233
Completed
Qwen3.6 27B MTP
Job #1232
Waiting
Qwen Coder
Job #1231
Active
Qwen3.6 27B MTP
Job #1230
Waiting
Qwen3.6 27B MTP
Job #1229
Failed
Qwen Coder
Job #1228
Waiting
Qwen3.6 27B MTP
⚠️ Warning
GPU 1 on hermes-03 approaching temperature threshold
10:23:38
⚠️ Warning
Server hermes-03 disk usage at 40%
10:23:38
⚠️ Warning
Job #1229 failed due to timeout
10:23:38
✅ Success
Job #1233 completed successfully
10:23:35
⚠️ Warning
Server hermes-02 network latency high
10:23:42
✅ Success
Model Qwen3.6 27B MTP loaded into memory
10:23:30