TEST #158 RESULTS
03/28/2025 - 11:13 PM
ACCELERATOR
MODEL
44.6
tokens/s
generation
689
ms
time to first token
2013
tokens/s
prompt
507
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E5-2690 v4 @ 2.60GHz (broadwell)
RAM
251.8GB
OS
Linux
Kernel Release
6.8.0-51-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #52-Ubuntu SMP PREEMPT_DYNAMIC Thu Dec 5 13:09:44 UTC 2024
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2332
tokens/s
46.0
tokens/s
461
ms
pp4096+tg256
1729
tokens/s
41.4
tokens/s
2.39
sec
pp2048+tg256
2073
tokens/s
44.2
tokens/s
1.01
sec
pp2048+tg768
2065
tokens/s
43.7
tokens/s
1.01
sec
pp1024+tg1024
2331
tokens/s
45.2
tokens/s
461
ms
pp1280+tg3072
2252
tokens/s
43.1
tokens/s
591
ms
pp384+tg1152
2661
tokens/s
45.7
tokens/s
167
ms
pp64+tg1024
2019
tokens/s
46.3
tokens/s
53
ms
pp16+tg1536
651
tokens/s
46.0
tokens/s
45
ms