TEST #1449 RESULTS
08/29/2025 - 2:52 AM
ACCELERATOR
MODEL
42.2
tokens/s
generation
1.07
sec
time to first token
1176
tokens/s
prompt
359
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
1280
tokens/s
43.4
tokens/s
823
ms
pp4096+tg256
1184
tokens/s
36.2
tokens/s
3.49
sec
pp2048+tg256
1340
tokens/s
39.3
tokens/s
1.55
sec
pp2048+tg768
1287
tokens/s
40.4
tokens/s
1.62
sec
pp1024+tg1024
1402
tokens/s
42.6
tokens/s
752
ms
pp1280+tg3072
1349
tokens/s
38.8
tokens/s
971
ms
pp384+tg1152
1376
tokens/s
45.7
tokens/s
299
ms
pp64+tg1024
1079
tokens/s
47.4
tokens/s
79
ms
pp16+tg1536
285
tokens/s
46.2
tokens/s
75
ms