TEST #3308 RESULTS
04/15/2026 - 3:39 AM
ACCELERATOR
MODEL
58.4
tokens/s
generation
683
ms
time to first token
1873
tokens/s
prompt
543
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
12th Gen Intel Core i9-12900K (alderlake)
RAM
91.8GB
OS
Linux
Kernel Release
6.8.0-107-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #107-Ubuntu SMP PREEMPT_DYNAMIC Fri Mar 13 19:51:50 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2231
tokens/s
61.6
tokens/s
475
ms
pp4096+tg256
1852
tokens/s
52.5
tokens/s
2.23
sec
pp2048+tg256
2063
tokens/s
57.7
tokens/s
1.01
sec
pp2048+tg768
2041
tokens/s
56.6
tokens/s
1.02
sec
pp1024+tg1024
2161
tokens/s
59.0
tokens/s
491
ms
pp1280+tg3072
2095
tokens/s
55.1
tokens/s
628
ms
pp384+tg1152
2188
tokens/s
60.3
tokens/s
194
ms
pp64+tg1024
1634
tokens/s
61.5
tokens/s
55
ms
pp16+tg1536
594
tokens/s
61.1
tokens/s
42
ms