TEST #407 RESULTS
04/06/2025 - 7:09 PM
ACCELERATOR
MODEL
368
tokens/s
generation
88
ms
time to first token
15252
tokens/s
prompt
3992
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5950X 16-Core Processor (znver3)
RAM
62.7GB
OS
Linux
Kernel Release
6.13.8-zen1-1.1-zen
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 ZEN SMP PREEMPT_DYNAMIC Mon, 24 Mar 2025 03:45:21 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
18314
tokens/s
370
tokens/s
59
ms
pp4096+tg256
13034
tokens/s
318
tokens/s
318
ms
pp2048+tg256
16847
tokens/s
358
tokens/s
124
ms
pp2048+tg768
16272
tokens/s
355
tokens/s
129
ms
pp1024+tg1024
19828
tokens/s
376
tokens/s
54
ms
pp1280+tg3072
18403
tokens/s
348
tokens/s
72
ms
pp384+tg1152
21588
tokens/s
388
tokens/s
20
ms
pp64+tg1024
11040
tokens/s
406
tokens/s
8
ms
pp16+tg1536
1938
tokens/s
395
tokens/s
11
ms