TEST #1423 RESULTS
08/24/2025 - 2:40 PM
ACCELERATOR
MODEL
39.6
tokens/s
generation
666
ms
time to first token
1995
tokens/s
prompt
491
LocalScore
HOW YOU STACK UP
Explore All ResultsLocal_Pretrained_Model - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 3900X 12-Core Processor (znver2)
RAM
31.3GB
OS
Linux
Kernel Release
6.16.1-arch1-1
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Fri, 15 Aug 2025 16:04:43 +0000
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2262
tokens/s
40.2
tokens/s
477
ms
pp4096+tg256
1802
tokens/s
36.8
tokens/s
2.30
sec
pp2048+tg256
2186
tokens/s
39.3
tokens/s
962
ms
pp2048+tg768
2189
tokens/s
38.9
tokens/s
961
ms
pp1024+tg1024
2465
tokens/s
40.0
tokens/s
440
ms
pp1280+tg3072
2418
tokens/s
38.5
tokens/s
554
ms
pp384+tg1152
2840
tokens/s
40.7
tokens/s
159
ms
pp64+tg1024
1399
tokens/s
41.1
tokens/s
83
ms
pp16+tg1536
392
tokens/s
40.9
tokens/s
65
ms