TEST #1384 RESULTS
08/15/2025 - 6:34 AM
ACCELERATOR
MODEL
45.5
tokens/s
generation
917
ms
time to first token
1497
tokens/s
prompt
420
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon W-11955M CPU @ 2.60GHz (tigerlake)
RAM
125.1GB
OS
Linux
Kernel Release
6.12.10-76061203-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #202412060638~1753385872~22.04~dc2e00d SMP PREEMPT_DYNAMIC Thu J
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1693
tokens/s
43.9
tokens/s
629
ms
pp4096+tg256
1274
tokens/s
42.0
tokens/s
3.24
sec
pp2048+tg256
1576
tokens/s
45.6
tokens/s
1.32
sec
pp2048+tg768
1578
tokens/s
44.9
tokens/s
1.32
sec
pp1024+tg1024
1707
tokens/s
46.4
tokens/s
620
ms
pp1280+tg3072
1656
tokens/s
43.7
tokens/s
794
ms
pp384+tg1152
1857
tokens/s
47.2
tokens/s
229
ms
pp64+tg1024
1538
tokens/s
48.0
tokens/s
61
ms
pp16+tg1536
595
tokens/s
47.4
tokens/s
45
ms