TEST #195 RESULTS
04/03/2025 - 7:54 PM
ACCELERATOR
MODEL
13.6
tokens/s
generation
502
ms
time to first token
2868
tokens/s
prompt
427
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon Platinum 8458P (sapphirerapids)
RAM
62.8GB
OS
Linux
Kernel Release
5.15.0-113-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #123-Ubuntu SMP Mon Jun 10 08:16:17 UTC 2024
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3962
tokens/s
13.6
tokens/s
331
ms
pp4096+tg256
2734
tokens/s
13.6
tokens/s
1.58
sec
pp2048+tg256
3555
tokens/s
13.5
tokens/s
655
ms
pp2048+tg768
3536
tokens/s
13.6
tokens/s
653
ms
pp1024+tg1024
3919
tokens/s
13.6
tokens/s
335
ms
pp1280+tg3072
3625
tokens/s
13.5
tokens/s
427
ms
pp384+tg1152
3714
tokens/s
13.7
tokens/s
178
ms
pp64+tg1024
612
tokens/s
13.9
tokens/s
179
ms
pp16+tg1536
155
tokens/s
13.8
tokens/s
177
ms