TEST #178 RESULTS
03/30/2025 - 8:19 PM
ACCELERATOR
MODEL
20.8
tokens/s
generation
1.07
sec
time to first token
1264
tokens/s
prompt
290
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 9800X3D 8-Core Processor
RAM
123.5GB
OS
Linux
Kernel Release
5.15.0-134-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #145-Ubuntu SMP Wed Feb 12 20:08:39 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1611
tokens/s
24.1
tokens/s
678
ms
pp4096+tg256
1083
tokens/s
14.4
tokens/s
3.85
sec
pp2048+tg256
1379
tokens/s
17.1
tokens/s
1.55
sec
pp2048+tg768
1375
tokens/s
17.2
tokens/s
1.55
sec
pp1024+tg1024
1617
tokens/s
22.4
tokens/s
676
ms
pp1280+tg3072
1497
tokens/s
17.1
tokens/s
901
ms
pp384+tg1152
1802
tokens/s
24.3
tokens/s
253
ms
pp64+tg1024
744
tokens/s
25.8
tokens/s
122
ms
pp16+tg1536
272
tokens/s
25.0
tokens/s
94
ms