TEST #2694 RESULTS
02/17/2026 - 8:35 AM
ACCELERATOR
MODEL
60.6
tokens/s
generation
652
ms
time to first token
1911
tokens/s
prompt
562
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i9-14900KF (alderlake)
RAM
62.6GB
OS
Linux
Kernel Release
6.19.0-rc7-1-MANJARO
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Mon, 26 Jan 2026 02:07:48 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2359
tokens/s
63.0
tokens/s
450
ms
pp4096+tg256
1940
tokens/s
54.2
tokens/s
2.13
sec
pp2048+tg256
2169
tokens/s
59.8
tokens/s
961
ms
pp2048+tg768
2179
tokens/s
58.7
tokens/s
957
ms
pp1024+tg1024
2321
tokens/s
61.4
tokens/s
457
ms
pp1280+tg3072
2268
tokens/s
57.6
tokens/s
581
ms
pp384+tg1152
2294
tokens/s
63.1
tokens/s
206
ms
pp64+tg1024
1322
tokens/s
64.2
tokens/s
64
ms
pp16+tg1536
349
tokens/s
63.6
tokens/s
60
ms