TEST #3691 RESULTS
06/06/2026 - 10:29 AM
ACCELERATOR
MODEL
64.2
tokens/s
generation
495
ms
time to first token
2781
tokens/s
prompt
712
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core Ultra 9 275HX (arrowlake-s)
RAM
15.5GB
OS
Linux
Kernel Release
6.6.114.1-microsoft-standard-WSL2
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Mon Dec 1 20:46:23 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2928
tokens/s
61.4
tokens/s
366
ms
pp4096+tg256
2268
tokens/s
59.0
tokens/s
1.82
sec
pp2048+tg256
3048
tokens/s
62.4
tokens/s
691
ms
pp2048+tg768
3066
tokens/s
62.6
tokens/s
685
ms
pp1024+tg1024
3709
tokens/s
70.9
tokens/s
291
ms
pp1280+tg3072
3330
tokens/s
61.9
tokens/s
401
ms
pp384+tg1152
3774
tokens/s
66.1
tokens/s
118
ms
pp64+tg1024
2121
tokens/s
66.4
tokens/s
46
ms
pp16+tg1536
787
tokens/s
67.2
tokens/s
34
ms