TEST #1399 RESULTS
08/20/2025 - 3:12 AM
ACCELERATOR
MODEL
43.3
tokens/s
generation
1.04
sec
time to first token
1224
tokens/s
prompt
371
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i9-7920X CPU @ 2.90GHz (skylake-avx512)
RAM
62.5GB
OS
Linux
Kernel Release
6.14.0-27-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #27~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Jul 22 17:38:49 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1458
tokens/s
46.7
tokens/s
725
ms
pp4096+tg256
1213
tokens/s
36.5
tokens/s
3.40
sec
pp2048+tg256
1359
tokens/s
42.3
tokens/s
1.53
sec
pp2048+tg768
1351
tokens/s
41.4
tokens/s
1.54
sec
pp1024+tg1024
1420
tokens/s
44.2
tokens/s
742
ms
pp1280+tg3072
1368
tokens/s
39.3
tokens/s
958
ms
pp384+tg1152
1394
tokens/s
45.3
tokens/s
296
ms
pp64+tg1024
1087
tokens/s
47.4
tokens/s
79
ms
pp16+tg1536
367
tokens/s
46.5
tokens/s
63
ms