TEST #1936 RESULTS
12/13/2025 - 3:00 PM
ACCELERATOR
MODEL
115
tokens/s
generation
188
ms
time to first token
6909
tokens/s
prompt
1618
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i9-14900K (alderlake)
RAM
62.6GB
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
8919
tokens/s
118
tokens/s
123
ms
pp4096+tg256
6342
tokens/s
105
tokens/s
656
ms
pp2048+tg256
7992
tokens/s
112
tokens/s
264
ms
pp2048+tg768
7831
tokens/s
113
tokens/s
270
ms
pp1024+tg1024
9191
tokens/s
115
tokens/s
119
ms
pp1280+tg3072
8844
tokens/s
111
tokens/s
153
ms
pp384+tg1152
8852
tokens/s
118
tokens/s
51
ms
pp64+tg1024
2836
tokens/s
123
tokens/s
31
ms
pp16+tg1536
1371
tokens/s
120
tokens/s
20
ms