TEST #1054 RESULTS
06/14/2025 - 10:53 PM
ACCELERATOR
MODEL
57.3
tokens/s
generation
773
ms
time to first token
1628
tokens/s
prompt
494
LocalScore
HOW YOU STACK UP
Explore All ResultsGemma 3 4b It - Q4_K - Medium
SYSTEM
CPU
AMD FX(tm)-8320 Eight-Core Processor (bdver2)
RAM
7.5GB
OS
Linux
Kernel Release
5.14.0-570.19.1.el9_6.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sat Jun 7 09:41:17 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1891
tokens/s
60.4
tokens/s
559
ms
pp4096+tg256
1660
tokens/s
45.1
tokens/s
2.49
sec
pp2048+tg256
1811
tokens/s
55.2
tokens/s
1.15
sec
pp2048+tg768
1799
tokens/s
53.6
tokens/s
1.16
sec
pp1024+tg1024
1870
tokens/s
59.0
tokens/s
564
ms
pp1280+tg3072
1840
tokens/s
51.0
tokens/s
713
ms
pp384+tg1152
1826
tokens/s
62.6
tokens/s
226
ms
pp64+tg1024
1370
tokens/s
65.4
tokens/s
61
ms
pp16+tg1536
583
tokens/s
63.6
tokens/s
42
ms