Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Inference Throughput on Llama-1B
Loading...
310.5
Throughput (Tokens/sec)
GPTQ
200.988
229.419
257.85
286.281
Jan 29, 2026
Throughput (Tokens/sec)
Updated 4d ago
Evaluation Results
Method
Method
Links
Throughput (Tokens/sec)
GPTQ
Quantization=W4A16, Ha...
2026.01
310.5
HeRo-Q
Quantization=W4A16, Ha...
2026.01
303.1
SpinQuant
Quantization=W4A16, Ha...
2026.01
302.8
FP16
Precision=FP16, Hardwa...
2026.01
205.2
Feedback
Search any
task
Search any
task
