Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Chatbot Workload Efficiency on LLaMA 2 70B
Loading...
315
GPU Power (W)
GPU-Only
313.92
321.21
328.5
335.79
Dec 11, 2025
GPU Power (W)
FPGA Power (W)
Total Power (W)
Energy per Token (J/token)
Updated 4d ago
Evaluation Results
Method
Method
Links
GPU Power (W)
FPGA Power (W)
Total Power (W)
Energy per Token (J/token)
GPU-Only
batch size=16
2025.12
315
0
315
0.647
CXL-SpecKV
batch size=64
2025.12
342
184
526
0.34
Feedback
Search any
task
Search any
task
