TEST #1935 RESULTS
12/13/2025 - 2:49 PM
ACCELERATOR
MODEL
65.6
tokens/s
generation
343
ms
time to first token
3809
tokens/s
prompt
900
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i9-14900K (alderlake)
RAM
62.6GB
OS
Linux
Kernel Release
6.14.0-37-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #37~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Nov 20 10:25:38 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4529
tokens/s
66.4
tokens/s
240
ms
pp4096+tg256
3511
tokens/s
60.1
tokens/s
1.18
sec
pp2048+tg256
4389
tokens/s
64.5
tokens/s
482
ms
pp2048+tg768
4298
tokens/s
63.9
tokens/s
492
ms
pp1024+tg1024
4924
tokens/s
66.8
tokens/s
223
ms
pp1280+tg3072
4756
tokens/s
63.9
tokens/s
285
ms
pp384+tg1152
4778
tokens/s
67.5
tokens/s
106
ms
pp64+tg1024
2316
tokens/s
69.2
tokens/s
41
ms
pp16+tg1536
781
tokens/s
68.4
tokens/s
34
ms