TEST #1106 RESULTS
06/25/2025 - 2:38 AM
ACCELERATOR
MODEL
14.9
tokens/s
generation
4.28
sec
time to first token
303
tokens/s
prompt
102
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon W-2235 CPU @ 3.80GHz (cascadelake)
RAM
62.5GB
OS
Linux
Kernel Release
6.11.0-26-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #26~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Apr 17 19:20:47 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
342
tokens/s
15.8
tokens/s
3.06
sec
pp4096+tg256
295
tokens/s
11.7
tokens/s
13.97
sec
pp2048+tg256
324
tokens/s
14.3
tokens/s
6.38
sec
pp2048+tg768
322
tokens/s
13.9
tokens/s
6.43
sec
pp1024+tg1024
338
tokens/s
15.3
tokens/s
3.09
sec
pp1280+tg3072
326
tokens/s
13.1
tokens/s
3.99
sec
pp384+tg1152
343
tokens/s
16.1
tokens/s
1.18
sec
pp64+tg1024
294
tokens/s
17.0
tokens/s
273
ms
pp16+tg1536
140
tokens/s
16.5
tokens/s
168
ms