TEST #2359 RESULTS
01/26/2026 - 8:00 PM
ACCELERATOR
MODEL
48.7
tokens/s
generation
665
ms
time to first token
1943
tokens/s
prompt
522
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
12th Gen Intel Core i9-12900K (alderlake)
RAM
31.7GB
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
2333
tokens/s
51.0
tokens/s
458
ms
pp4096+tg256
1893
tokens/s
44.3
tokens/s
2.19
sec
pp2048+tg256
2158
tokens/s
48.2
tokens/s
969
ms
pp2048+tg768
2156
tokens/s
47.5
tokens/s
970
ms
pp1024+tg1024
2300
tokens/s
48.9
tokens/s
464
ms
pp1280+tg3072
2221
tokens/s
46.6
tokens/s
595
ms
pp384+tg1152
2369
tokens/s
50.1
tokens/s
229
ms
pp64+tg1024
1627
tokens/s
51.0
tokens/s
58
ms
pp16+tg1536
427
tokens/s
50.6
tokens/s
55
ms