TEST #3160 RESULTS
03/23/2026 - 10:36 AM
ACCELERATOR
MODEL
78.7
tokens/s
generation
721
ms
time to first token
1879
tokens/s
prompt
590
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Celeron G4900 CPU @ 3.10GHz (skylake)
RAM
7.6GB
OS
Linux
Kernel Release
5.15.0-173-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #183-Ubuntu SMP Fri Mar 6 13:29:34 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2180
tokens/s
86.1
tokens/s
481
ms
pp4096+tg256
1632
tokens/s
53.1
tokens/s
2.53
sec
pp2048+tg256
1967
tokens/s
71.5
tokens/s
1.06
sec
pp2048+tg768
1961
tokens/s
68.5
tokens/s
1.06
sec
pp1024+tg1024
2162
tokens/s
80.8
tokens/s
485
ms
pp1280+tg3072
2076
tokens/s
64.1
tokens/s
628
ms
pp384+tg1152
2282
tokens/s
90.7
tokens/s
178
ms
pp64+tg1024
1821
tokens/s
99.1
tokens/s
44
ms
pp16+tg1536
828
tokens/s
94.3
tokens/s
28
ms