TEST #2271 RESULTS
01/13/2026 - 2:34 AM
ACCELERATOR
MODEL
39.1
tokens/s
generation
1.12
sec
time to first token
1084
tokens/s
prompt
336
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon W-2133 CPU @ 3.60GHz (skylake-avx512)
RAM
94.3GB
OS
Linux
Kernel Release
6.8.0-90-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #91-Ubuntu SMP PREEMPT_DYNAMIC Tue Nov 18 14:14:30 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1374
tokens/s
45.4
tokens/s
767
ms
pp4096+tg256
1155
tokens/s
31.5
tokens/s
3.57
sec
pp2048+tg256
1284
tokens/s
40.8
tokens/s
1.62
sec
pp2048+tg768
1275
tokens/s
39.5
tokens/s
1.63
sec
pp1024+tg1024
1293
tokens/s
40.4
tokens/s
815
ms
pp1280+tg3072
1175
tokens/s
34.0
tokens/s
1.11
sec
pp384+tg1152
1061
tokens/s
39.2
tokens/s
385
ms
pp64+tg1024
910
tokens/s
40.7
tokens/s
92
ms
pp16+tg1536
227
tokens/s
40.2
tokens/s
92
ms