TEST #92 RESULTS
03/28/2025 - 9:26 PM
ACCELERATOR
MODEL
42.4
tokens/s
generation
263
ms
time to first token
4687
tokens/s
prompt
911
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon Platinum 8470 (sapphirerapids)
RAM
1007.3GB
OS
Linux
Kernel Release
6.8.0-48-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #48~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Oct 7 11:24:13 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
6059
tokens/s
44.4
tokens/s
191
ms
pp4096+tg256
5473
tokens/s
37.7
tokens/s
778
ms
pp2048+tg256
5976
tokens/s
41.3
tokens/s
367
ms
pp2048+tg768
5977
tokens/s
40.8
tokens/s
367
ms
pp1024+tg1024
6131
tokens/s
42.6
tokens/s
190
ms
pp1280+tg3072
5534
tokens/s
40.0
tokens/s
255
ms
pp384+tg1152
5390
tokens/s
43.3
tokens/s
91
ms
pp64+tg1024
1160
tokens/s
46.2
tokens/s
74
ms
pp16+tg1536
482
tokens/s
45.4
tokens/s
52
ms