TEST #1009 RESULTS
06/06/2025 - 3:06 PM
ACCELERATOR
MODEL
44.5
tokens/s
generation
1.33
sec
time to first token
1013
tokens/s
prompt
324
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i7 CPU 870 @ 2.93GHz (nehalem)
RAM
15.5GB
OS
Linux
Kernel Release
6.6.90-1-MANJARO
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Fri May 9 12:16:05 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1144
tokens/s
47.9
tokens/s
916
ms
pp4096+tg256
905
tokens/s
30.1
tokens/s
4.56
sec
pp2048+tg256
1063
tokens/s
40.6
tokens/s
1.95
sec
pp2048+tg768
1058
tokens/s
38.9
tokens/s
1.96
sec
pp1024+tg1024
1156
tokens/s
45.7
tokens/s
906
ms
pp1280+tg3072
1121
tokens/s
36.3
tokens/s
1.16
sec
pp384+tg1152
1195
tokens/s
51.4
tokens/s
339
ms
pp64+tg1024
1028
tokens/s
56.4
tokens/s
78
ms
pp16+tg1536
449
tokens/s
53.5
tokens/s
51
ms