Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM Decoding on Llama-2 70B (Throughput)
Loading...
36.1
Throughput (tokens/s)
AWQ
16.86
21.855
26.85
31.845
Jun 2, 2026
Throughput (tokens/s)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Throughput (tokens/s)
AWQ
Quantization Configura...
2026.06
36.1
LIFTQUANT
Quantization Configura...
2026.06
31.3
LIFTQUANT
Quantization Configura...
2026.06
25.7
QTIP
Quantization Configura...
2026.06
24.5
LIFTQUANT
Quantization Configura...
2026.06
20.8
QTIP
Quantization Configura...
2026.06
17.6
Feedback
Search any
task
Search any
task