TEST #1595 RESULTS
10/06/2025 - 11:05 PM
ACCELERATOR
MODEL
36.5
tokens/s
generation
1.75
sec
time to first token
825
tokens/s
prompt
258
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-10400 CPU @ 2.90GHz (skylake)
RAM
31.3GB
OS
Linux
Kernel Release
6.8.0-84-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #84-Ubuntu SMP PREEMPT_DYNAMIC Fri Sep 5 22:36:38 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
898
tokens/s
44.2
tokens/s
1.16
sec
pp4096+tg256
663
tokens/s
13.9
tokens/s
6.25
sec
pp2048+tg256
802
tokens/s
25.0
tokens/s
2.59
sec
pp2048+tg768
803
tokens/s
22.6
tokens/s
2.59
sec
pp1024+tg1024
890
tokens/s
33.3
tokens/s
1.17
sec
pp1280+tg3072
867
tokens/s
19.7
tokens/s
1.50
sec
pp384+tg1152
954
tokens/s
47.5
tokens/s
415
ms
pp64+tg1024
963
tokens/s
67.3
tokens/s
73
ms
pp16+tg1536
589
tokens/s
55.0
tokens/s
33
ms