TEST #2792 RESULTS
02/23/2026 - 3:40 AM
ACCELERATOR
MODEL
29.7
tokens/s
generation
1.36
sec
time to first token
1159
tokens/s
prompt
293
LocalScore
HOW YOU STACK UP
Explore All ResultsDeepSeek R1 0528 Qwen3 8B - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-14450HX (alderlake)
RAM
15.7GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1331
tokens/s
30.6
tokens/s
803
ms
pp4096+tg256
703
tokens/s
26.9
tokens/s
5.87
sec
pp2048+tg256
1234
tokens/s
29.3
tokens/s
1.69
sec
pp2048+tg768
1225
tokens/s
29.1
tokens/s
1.70
sec
pp1024+tg1024
1398
tokens/s
30.0
tokens/s
765
ms
pp1280+tg3072
1328
tokens/s
28.7
tokens/s
997
ms
pp384+tg1152
1584
tokens/s
30.9
tokens/s
274
ms
pp64+tg1024
1265
tokens/s
31.1
tokens/s
82
ms
pp16+tg1536
359
tokens/s
30.8
tokens/s
76
ms