TEST #3866 RESULTS
07/06/2026 - 6:06 PM
ACCELERATOR
MODEL
103
tokens/s
generation
365
ms
time to first token
3510
tokens/s
prompt
997
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-14400 (alderlake)
RAM
125.6GB
OS
Linux
Kernel Release
6.17.0-35-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #35~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue May 26 19:30:42 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3684
tokens/s
105
tokens/s
288
ms
pp4096+tg256
3408
tokens/s
92.9
tokens/s
1.21
sec
pp2048+tg256
3947
tokens/s
102
tokens/s
529
ms
pp2048+tg768
3944
tokens/s
101
tokens/s
529
ms
pp1024+tg1024
4277
tokens/s
104
tokens/s
249
ms
pp1280+tg3072
4124
tokens/s
98.5
tokens/s
320
ms
pp384+tg1152
4437
tokens/s
105
tokens/s
96
ms
pp64+tg1024
3027
tokens/s
109
tokens/s
30
ms
pp16+tg1536
745
tokens/s
108
tokens/s
30
ms