TEST #1484 RESULTS
09/05/2025 - 4:41 AM
ACCELERATOR
MODEL
41.5
tokens/s
generation
1.43
sec
time to first token
959
tokens/s
prompt
303
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-8300H CPU @ 2.30GHz (skylake)
RAM
15.5GB
OS
Linux
Kernel Release
6.14.0-29-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #29~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Aug 14 16:52:50 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1089
tokens/s
48.1
tokens/s
961
ms
pp4096+tg256
837
tokens/s
25.7
tokens/s
4.93
sec
pp2048+tg256
987
tokens/s
37.7
tokens/s
2.10
sec
pp2048+tg768
982
tokens/s
35.7
tokens/s
2.11
sec
pp1024+tg1024
1076
tokens/s
42.4
tokens/s
974
ms
pp1280+tg3072
1033
tokens/s
32.8
tokens/s
1.26
sec
pp384+tg1152
1101
tokens/s
48.1
tokens/s
367
ms
pp64+tg1024
1017
tokens/s
53.1
tokens/s
79
ms
pp16+tg1536
510
tokens/s
50.0
tokens/s
47
ms