TEST #1332 RESULTS
08/07/2025 - 8:13 AM
ACCELERATOR
MODEL
66.8
tokens/s
generation
710
ms
time to first token
1921
tokens/s
prompt
565
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q8_0
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
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2258
tokens/s
72.5
tokens/s
467
ms
pp4096+tg256
1648
tokens/s
47.3
tokens/s
2.51
sec
pp2048+tg256
2009
tokens/s
61.8
tokens/s
1.04
sec
pp2048+tg768
1996
tokens/s
59.3
tokens/s
1.04
sec
pp1024+tg1024
2232
tokens/s
68.4
tokens/s
472
ms
pp1280+tg3072
2135
tokens/s
56.2
tokens/s
614
ms
pp384+tg1152
2364
tokens/s
75.6
tokens/s
174
ms
pp64+tg1024
1896
tokens/s
81.6
tokens/s
45
ms
pp16+tg1536
753
tokens/s
78.2
tokens/s
32
ms