TEST #1242 RESULTS
07/23/2025 - 9:24 AM
ACCELERATOR
MODEL
34.0
tokens/s
generation
933
ms
time to first token
1429
tokens/s
prompt
373
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E5-2699 v3 @ 2.30GHz (haswell)
RAM
62.8GB
OS
Linux
Kernel Release
6.15.7-arch1-1
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Thu, 17 Jul 2025 21:05:29 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1674
tokens/s
35.0
tokens/s
640
ms
pp4096+tg256
1320
tokens/s
30.9
tokens/s
3.14
sec
pp2048+tg256
1532
tokens/s
33.6
tokens/s
1.37
sec
pp2048+tg768
1530
tokens/s
33.2
tokens/s
1.37
sec
pp1024+tg1024
1666
tokens/s
34.3
tokens/s
643
ms
pp1280+tg3072
1615
tokens/s
32.6
tokens/s
822
ms
pp384+tg1152
1825
tokens/s
35.1
tokens/s
238
ms
pp64+tg1024
1242
tokens/s
35.7
tokens/s
121
ms
pp16+tg1536
458
tokens/s
35.3
tokens/s
62
ms