TEST #171 RESULTS
03/30/2025 - 8:11 PM
ACCELERATOR
MODEL
47.7
tokens/s
generation
859
ms
time to first token
2317
tokens/s
prompt
505
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-14600KF (alderlake)
RAM
62.6GB
OS
Linux
Kernel Release
6.8.0-52-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #53~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Jan 15 19:18:46 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2863
tokens/s
52.2
tokens/s
377
ms
pp4096+tg256
2071
tokens/s
35.6
tokens/s
2.01
sec
pp2048+tg256
2537
tokens/s
45.0
tokens/s
830
ms
pp2048+tg768
2530
tokens/s
43.6
tokens/s
832
ms
pp1024+tg1024
2892
tokens/s
48.9
tokens/s
374
ms
pp1280+tg3072
2711
tokens/s
41.2
tokens/s
492
ms
pp384+tg1152
3194
tokens/s
52.7
tokens/s
138
ms
pp64+tg1024
2045
tokens/s
55.8
tokens/s
48
ms
pp16+tg1536
6
tokens/s
54.1
tokens/s
2.63
sec