TEST #3322 RESULTS
04/15/2026 - 10:53 PM
ACCELERATOR
MODEL
30.5
tokens/s
generation
1.38
sec
time to first token
915
tokens/s
prompt
273
LocalScore
HOW YOU STACK UP
Explore All ResultsQwQ 32B - 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
1064
tokens/s
31.8
tokens/s
994
ms
pp4096+tg256
944
tokens/s
28.2
tokens/s
4.38
sec
pp2048+tg256
1010
tokens/s
30.3
tokens/s
2.06
sec
pp2048+tg768
1004
tokens/s
29.9
tokens/s
2.07
sec
pp1024+tg1024
1038
tokens/s
30.8
tokens/s
1.02
sec
pp1280+tg3072
1015
tokens/s
29.2
tokens/s
1.29
sec
pp384+tg1152
1018
tokens/s
31.3
tokens/s
416
ms
pp64+tg1024
856
tokens/s
31.8
tokens/s
105
ms
pp16+tg1536
285
tokens/s
31.5
tokens/s
86
ms