TEST #830 RESULTS
05/06/2025 - 12:54 AM
ACCELERATOR
MODEL
105
tokens/s
generation
317
ms
time to first token
4158
tokens/s
prompt
1111
LocalScore
HOW YOU STACK UP
Explore All ResultsEXAONE-Deep-2.4B - Q4_K - Medium
SYSTEM
CPU
Intel Xeon W-3235 CPU @ 3.30GHz (cascadelake)
RAM
41GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
5354
tokens/s
113
tokens/s
201
ms
pp4096+tg256
3694
tokens/s
85.0
tokens/s
1.12
sec
pp2048+tg256
4611
tokens/s
103
tokens/s
454
ms
pp2048+tg768
4604
tokens/s
98.5
tokens/s
456
ms
pp1024+tg1024
5188
tokens/s
107
tokens/s
206
ms
pp1280+tg3072
4937
tokens/s
93.8
tokens/s
268
ms
pp384+tg1152
5562
tokens/s
112
tokens/s
80
ms
pp64+tg1024
2989
tokens/s
115
tokens/s
29
ms
pp16+tg1536
481
tokens/s
115
tokens/s
41
ms