TEST #3027 RESULTS
03/07/2026 - 10:28 PM
ACCELERATOR
MODEL
33.1
tokens/s
generation
1.23
sec
time to first token
1057
tokens/s
prompt
306
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E5-2699A v4 @ 2.40GHz (broadwell)
RAM
503.7GB
OS
Linux
Kernel Release
6.18.9-arch1-2.1
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Wed, 11 Feb 2026 13:53:26 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1267
tokens/s
35.0
tokens/s
836
ms
pp4096+tg256
1031
tokens/s
30.6
tokens/s
4.01
sec
pp2048+tg256
1156
tokens/s
32.9
tokens/s
1.80
sec
pp2048+tg768
1146
tokens/s
32.4
tokens/s
1.82
sec
pp1024+tg1024
1203
tokens/s
33.4
tokens/s
881
ms
pp1280+tg3072
1152
tokens/s
31.3
tokens/s
1.14
sec
pp384+tg1152
1232
tokens/s
34.0
tokens/s
340
ms
pp64+tg1024
1019
tokens/s
34.5
tokens/s
132
ms
pp16+tg1536
303
tokens/s
34.2
tokens/s
84
ms