TEST #1234 RESULTS
07/22/2025 - 2:25 AM
ACCELERATOR
MODEL
79.7
tokens/s
generation
246
ms
time to first token
5072
tokens/s
prompt
1180
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen Threadripper 3970X 32-Core Processor (znver2)
RAM
125.6GB
OS
Linux
Kernel Release
6.8.0-60-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #63-Ubuntu SMP PREEMPT_DYNAMIC Tue Apr 15 19:04:15 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
5496
tokens/s
81.4
tokens/s
199
ms
pp4096+tg256
5217
tokens/s
70.8
tokens/s
809
ms
pp2048+tg256
6272
tokens/s
79.1
tokens/s
339
ms
pp2048+tg768
6276
tokens/s
78.3
tokens/s
340
ms
pp1024+tg1024
6643
tokens/s
80.5
tokens/s
167
ms
pp1280+tg3072
6302
tokens/s
76.3
tokens/s
216
ms
pp384+tg1152
5901
tokens/s
83.5
tokens/s
77
ms
pp64+tg1024
2608
tokens/s
84.9
tokens/s
37
ms
pp16+tg1536
930
tokens/s
82.8
tokens/s
30
ms