TEST #1761 RESULTS
11/08/2025 - 4:11 PM
ACCELERATOR
MODEL
53.1
tokens/s
generation
664
ms
time to first token
2089
tokens/s
prompt
551
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon Gold 6138 CPU @ 2.00GHz (skylake-avx512)
RAM
93GB
OS
Linux
Kernel Release
6.14.0-35-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #35~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Oct 14 13:55:17 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1265
tokens/s
58.1
tokens/s
826
ms
pp4096+tg256
1861
tokens/s
39.1
tokens/s
2.23
sec
pp2048+tg256
2330
tokens/s
49.0
tokens/s
898
ms
pp2048+tg768
2426
tokens/s
48.1
tokens/s
864
ms
pp1024+tg1024
2799
tokens/s
54.4
tokens/s
383
ms
pp1280+tg3072
2709
tokens/s
45.9
tokens/s
490
ms
pp384+tg1152
3187
tokens/s
59.2
tokens/s
136
ms
pp64+tg1024
2049
tokens/s
62.9
tokens/s
46
ms
pp16+tg1536
175
tokens/s
60.8
tokens/s
107
ms