TEST #3136 RESULTS
03/20/2026 - 6:14 PM
ACCELERATOR
MODEL
36.3
tokens/s
generation
1.48
sec
time to first token
887
tokens/s
prompt
279
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Phenom(tm) 9550 Quad-Core Processor (amdfam10)
RAM
3.6GB
OS
Linux
Kernel Release
6.8.0-101-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #101-Ubuntu SMP PREEMPT_DYNAMIC Mon Feb 9 10:15:05 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1039
tokens/s
39.0
tokens/s
1.01
sec
pp4096+tg256
814
tokens/s
24.6
tokens/s
5.08
sec
pp2048+tg256
947
tokens/s
33.4
tokens/s
2.19
sec
pp2048+tg768
947
tokens/s
31.8
tokens/s
2.19
sec
pp1024+tg1024
1028
tokens/s
37.4
tokens/s
1.02
sec
pp1280+tg3072
992
tokens/s
29.8
tokens/s
1.32
sec
pp384+tg1152
1051
tokens/s
41.9
tokens/s
387
ms
pp64+tg1024
826
tokens/s
45.6
tokens/s
97
ms
pp16+tg1536
341
tokens/s
43.6
tokens/s
66
ms