TEST #2316 RESULTS
01/16/2026 - 10:05 PM
ACCELERATOR
MODEL
109
tokens/s
generation
335
ms
time to first token
3858
tokens/s
prompt
1080
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
6.14.0-37-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #37~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Nov 20 10:25:38 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4589
tokens/s
111
tokens/s
232
ms
pp4096+tg256
3681
tokens/s
98.6
tokens/s
1.12
sec
pp2048+tg256
4208
tokens/s
108
tokens/s
496
ms
pp2048+tg768
4263
tokens/s
107
tokens/s
490
ms
pp1024+tg1024
4599
tokens/s
111
tokens/s
232
ms
pp1280+tg3072
4432
tokens/s
105
tokens/s
298
ms
pp384+tg1152
4770
tokens/s
113
tokens/s
89
ms
pp64+tg1024
3352
tokens/s
116
tokens/s
27
ms
pp16+tg1536
832
tokens/s
114
tokens/s
27
ms