TEST #1322 RESULTS
08/07/2025 - 5:41 AM
ACCELERATOR
MODEL
78.0
tokens/s
generation
724
ms
time to first token
1875
tokens/s
prompt
587
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-6600K CPU @ 3.50GHz (skylake)
RAM
15.1GB
OS
Linux
Kernel Release
6.14.0-27-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #27-Ubuntu SMP PREEMPT_DYNAMIC Tue Jul 22 17:01:58 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2190
tokens/s
85.7
tokens/s
479
ms
pp4096+tg256
1617
tokens/s
52.4
tokens/s
2.55
sec
pp2048+tg256
1956
tokens/s
70.8
tokens/s
1.06
sec
pp2048+tg768
1954
tokens/s
67.6
tokens/s
1.06
sec
pp1024+tg1024
2171
tokens/s
79.9
tokens/s
483
ms
pp1280+tg3072
2086
tokens/s
63.7
tokens/s
626
ms
pp384+tg1152
2322
tokens/s
90.2
tokens/s
175
ms
pp64+tg1024
1792
tokens/s
98.4
tokens/s
45
ms
pp16+tg1536
787
tokens/s
93.8
tokens/s
29
ms