TEST #3162 RESULTS
03/23/2026 - 12:01 PM
ACCELERATOR
MODEL
42.1
tokens/s
generation
1.40
sec
time to first token
958
tokens/s
prompt
307
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
6.8.0-106-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #106-Ubuntu SMP PREEMPT_DYNAMIC Fri Mar 6 07:58:08 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1095
tokens/s
48.0
tokens/s
957
ms
pp4096+tg256
869
tokens/s
28.1
tokens/s
4.75
sec
pp2048+tg256
997
tokens/s
38.6
tokens/s
2.08
sec
pp2048+tg768
997
tokens/s
36.7
tokens/s
2.08
sec
pp1024+tg1024
1076
tokens/s
43.2
tokens/s
973
ms
pp1280+tg3072
1042
tokens/s
34.1
tokens/s
1.25
sec
pp384+tg1152
1070
tokens/s
48.1
tokens/s
378
ms
pp64+tg1024
1003
tokens/s
52.4
tokens/s
80
ms
pp16+tg1536
475
tokens/s
49.9
tokens/s
50
ms