TEST #1741 RESULTS
11/05/2025 - 7:57 PM
ACCELERATOR
MODEL
93.9
tokens/s
generation
598
ms
time to first token
2197
tokens/s
prompt
702
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon Gold 6138 CPU @ 2.00GHz (skylake-avx512)
RAM
93GB
OS
Linux
Kernel Release
6.14.0-35-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #35~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Oct 14 13:55:17 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2611
tokens/s
98.7
tokens/s
402
ms
pp4096+tg256
2013
tokens/s
64.2
tokens/s
2.05
sec
pp2048+tg256
2366
tokens/s
86.6
tokens/s
877
ms
pp2048+tg768
2348
tokens/s
83.5
tokens/s
884
ms
pp1024+tg1024
2571
tokens/s
97.7
tokens/s
409
ms
pp1280+tg3072
2423
tokens/s
78.5
tokens/s
538
ms
pp384+tg1152
2682
tokens/s
108
tokens/s
151
ms
pp64+tg1024
1924
tokens/s
117
tokens/s
40
ms
pp16+tg1536
839
tokens/s
112
tokens/s
26
ms