TEST #690 RESULTS
04/11/2025 - 11:56 AM
ACCELERATOR
MODEL
10.8
tokens/s
generation
8.84
sec
time to first token
247
tokens/s
prompt
67
LocalScore
HOW YOU STACK UP
Explore All ResultsCogito v1 Preview Qwen 14B - Q4_K - Medium
SYSTEM
CPU
13th Gen Intel Core i7-13700K (alderlake)
RAM
63.8GB
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
284
tokens/s
14.3
tokens/s
3.68
sec
pp4096+tg256
169
tokens/s
5.0
tokens/s
24.48
sec
pp2048+tg256
233
tokens/s
9.1
tokens/s
8.89
sec
pp2048+tg768
229
tokens/s
7.9
tokens/s
9.07
sec
pp1024+tg1024
290
tokens/s
5.1
tokens/s
3.60
sec
pp1280+tg3072
45
tokens/s
5.4
tokens/s
28.33
sec
pp384+tg1152
338
tokens/s
14.5
tokens/s
1.18
sec
pp64+tg1024
381
tokens/s
19.4
tokens/s
218
ms
pp16+tg1536
253
tokens/s
16.2
tokens/s
93
ms