TEST #714 RESULTS
04/14/2025 - 7:06 AM
ACCELERATOR
MODEL
41.3
tokens/s
generation
208
ms
time to first token
6298
tokens/s
prompt
1077
LocalScore
HOW YOU STACK UP
Explore All ResultsPhi3 - F16
SYSTEM
CPU
AMD Ryzen 9 7900 12-Core Processor (znver4)
RAM
61.9GB
OS
Linux
Kernel Release
6.8.0-57-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #59-Ubuntu SMP PREEMPT_DYNAMIC Sat Mar 15 17:40:59 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
5785
tokens/s
46.4
tokens/s
199
ms
pp4096+tg256
6726
tokens/s
34.6
tokens/s
638
ms
pp2048+tg256
8137
tokens/s
39.9
tokens/s
277
ms
pp2048+tg768
8359
tokens/s
38.6
tokens/s
270
ms
pp1024+tg1024
9189
tokens/s
41.6
tokens/s
135
ms
pp1280+tg3072
8110
tokens/s
37.5
tokens/s
182
ms
pp384+tg1152
7604
tokens/s
43.5
tokens/s
72
ms
pp64+tg1024
2293
tokens/s
45.2
tokens/s
48
ms
pp16+tg1536
482
tokens/s
44.3
tokens/s
53
ms