TEST #1048 RESULTS

06/14/2025 - 12:25 AM

57.4

tokens/s

generation

745

ms

time to first token

1689

tokens/s

prompt

507

LocalScore

HOW YOU STACK UP
Explore All Results

Gemma 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
1979
tokens/s
61.0
tokens/s
534
ms
pp4096+tg256
1723
tokens/s
45.1
tokens/s
2.40
sec
pp2048+tg256
1876
tokens/s
55.1
tokens/s
1.11
sec
pp2048+tg768
1872
tokens/s
53.6
tokens/s
1.11
sec
pp1024+tg1024
1951
tokens/s
58.9
tokens/s
541
ms
pp1280+tg3072
1906
tokens/s
51.0
tokens/s
688
ms
pp384+tg1152
1922
tokens/s
62.6
tokens/s
215
ms
pp64+tg1024
1382
tokens/s
65.4
tokens/s
61
ms
pp16+tg1536
588
tokens/s
63.8
tokens/s
41
ms