TEST #2041 RESULTS
12/25/2025 - 9:31 PM
ACCELERATOR
MODEL
78.4
tokens/s
generation
98
ms
time to first token
13821
tokens/s
prompt
2229
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon Gold 5418Y (sapphirerapids)
RAM
701.2GB
OS
Linux
Kernel Release
6.8.0-90-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #91-Ubuntu SMP PREEMPT_DYNAMIC Tue Nov 18 14:14:30 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
19042
tokens/s
94.8
tokens/s
64
ms
pp4096+tg256
15078
tokens/s
81.4
tokens/s
290
ms
pp2048+tg256
18148
tokens/s
81.7
tokens/s
124
ms
pp2048+tg768
18007
tokens/s
70.3
tokens/s
128
ms
pp1024+tg1024
18573
tokens/s
70.1
tokens/s
71
ms
pp1280+tg3072
16478
tokens/s
70.1
tokens/s
93
ms
pp384+tg1152
15431
tokens/s
72.0
tokens/s
38
ms
pp64+tg1024
2942
tokens/s
76.4
tokens/s
35
ms
pp16+tg1536
691
tokens/s
88.4
tokens/s
37
ms