TEST #1378 RESULTS
08/14/2025 - 8:43 PM
ACCELERATOR
MODEL
35.1
tokens/s
generation
937
ms
time to first token
1410
tokens/s
prompt
375
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E5-2650L v3 @ 1.80GHz (haswell)
RAM
62.7GB
OS
Linux
Kernel Release
6.8.12-13-pve
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC PMX 6.8.12-13 (2025-07-22T10:00Z)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1642
tokens/s
35.3
tokens/s
652
ms
pp4096+tg256
1322
tokens/s
32.2
tokens/s
3.13
sec
pp2048+tg256
1531
tokens/s
34.2
tokens/s
1.37
sec
pp2048+tg768
1533
tokens/s
34.3
tokens/s
1.37
sec
pp1024+tg1024
1648
tokens/s
35.7
tokens/s
650
ms
pp1280+tg3072
1610
tokens/s
33.9
tokens/s
824
ms
pp384+tg1152
1753
tokens/s
36.5
tokens/s
247
ms
pp64+tg1024
1200
tokens/s
36.8
tokens/s
131
ms
pp16+tg1536
448
tokens/s
36.7
tokens/s
63
ms