TEST #2340 RESULTS
01/21/2026 - 3:18 PM
ACCELERATOR
MODEL
33.1
tokens/s
generation
503
ms
time to first token
2475
tokens/s
prompt
546
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
13th Gen Intel Core i5-1335U (alderlake)
RAM
63.2GB
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
3089
tokens/s
34.5
tokens/s
354
ms
pp4096+tg256
2562
tokens/s
31.0
tokens/s
1.62
sec
pp2048+tg256
2930
tokens/s
32.6
tokens/s
720
ms
pp2048+tg768
2881
tokens/s
32.3
tokens/s
734
ms
pp1024+tg1024
3623
tokens/s
33.4
tokens/s
303
ms
pp1280+tg3072
3048
tokens/s
32.1
tokens/s
475
ms
pp384+tg1152
2670
tokens/s
33.7
tokens/s
165
ms
pp64+tg1024
1206
tokens/s
34.1
tokens/s
74
ms
pp16+tg1536
270
tokens/s
34.1
tokens/s
80
ms