Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
CPU Inference Performance Evaluation on DeepSeek Lite V2
Loading...
8.8
Memory Usage (GB)
Llama.cpp (CPU)
7.98
13.515
19.05
24.585
Apr 12, 2026
Memory Usage (GB)
Latency (s)
Updated 5d ago
Evaluation Results
Method
Method
Links
Memory Usage (GB)
Latency (s)
Llama.cpp (CPU)
Bit Width=A8W4, Hardwa...
2026.04
8.8
17.1
CodeQuant (CPU)
Bit Width=A8W4, Hardwa...
2026.04
8.9
14.2
Llama.cpp (CPU)
Bit Width=BF16, Hardwa...
2026.04
29.3
50
Feedback
Search any
task
Search any
task