TEST #2374 RESULTS
01/30/2026 - 12:15 PM
ACCELERATOR
MODEL
31.0
tokens/s
generation
1.46
sec
time to first token
1185
tokens/s
prompt
293
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-14450HX (alderlake)
RAM
15.7GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1359
tokens/s
31.8
tokens/s
786
ms
pp4096+tg256
577
tokens/s
28.8
tokens/s
7.13
sec
pp2048+tg256
1337
tokens/s
31.4
tokens/s
1.56
sec
pp2048+tg768
1341
tokens/s
31.3
tokens/s
1.56
sec
pp1024+tg1024
1493
tokens/s
32.1
tokens/s
716
ms
pp1280+tg3072
1440
tokens/s
30.1
tokens/s
920
ms
pp384+tg1152
1519
tokens/s
30.5
tokens/s
284
ms
pp64+tg1024
1231
tokens/s
31.8
tokens/s
85
ms
pp16+tg1536
368
tokens/s
31.4
tokens/s
74
ms