TEST #1116 RESULTS
06/25/2025 - 5:37 PM
ACCELERATOR
MODEL
72.6
tokens/s
generation
2.21
sec
time to first token
599
tokens/s
prompt
270
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i9-14900K (alderlake)
RAM
94GB
OS
Linux
Kernel Release
6.11.0-26-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #26~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Apr 17 19:20:47 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
679
tokens/s
96.1
tokens/s
1.52
sec
pp4096+tg256
551
tokens/s
5.0
tokens/s
7.63
sec
pp2048+tg256
630
tokens/s
56.4
tokens/s
3.27
sec
pp2048+tg768
629
tokens/s
52.2
tokens/s
3.27
sec
pp1024+tg1024
680
tokens/s
74.4
tokens/s
1.52
sec
pp1280+tg3072
661
tokens/s
26.7
tokens/s
1.95
sec
pp384+tg1152
685
tokens/s
100
tokens/s
567
ms
pp64+tg1024
375
tokens/s
130
tokens/s
176
ms
pp16+tg1536
502
tokens/s
112
tokens/s
36
ms