TEST #66 RESULTS
03/28/2025 - 8:58 PM
ACCELERATOR
MODEL
66.3
tokens/s
generation
592
ms
time to first token
2069
tokens/s
prompt
614
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 7713 64-Core Processor (znver3)
RAM
1007.7GB
OS
Linux
Kernel Release
6.5.0-28-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #29~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Apr 4 14:39:20 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2436
tokens/s
68.2
tokens/s
435
ms
pp4096+tg256
2217
tokens/s
61.0
tokens/s
1.86
sec
pp2048+tg256
2365
tokens/s
65.4
tokens/s
883
ms
pp2048+tg768
2373
tokens/s
64.9
tokens/s
878
ms
pp1024+tg1024
2474
tokens/s
66.9
tokens/s
428
ms
pp1280+tg3072
2383
tokens/s
64.1
tokens/s
552
ms
pp384+tg1152
2403
tokens/s
68.4
tokens/s
174
ms
pp64+tg1024
1504
tokens/s
69.3
tokens/s
68
ms
pp16+tg1536
461
tokens/s
68.7
tokens/s
49
ms