TEST #1338 RESULTS
08/07/2025 - 10:09 PM
ACCELERATOR
MODEL
122
tokens/s
generation
73
ms
time to first token
17723
tokens/s
prompt
3098
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 9950X3D 16-Core Processor
RAM
62.3GB
OS
Linux
Kernel Release
6.14.0-27-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #27~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Jul 22 17:38:49 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
24161
tokens/s
135
tokens/s
50
ms
pp4096+tg256
19890
tokens/s
99.6
tokens/s
216
ms
pp2048+tg256
21905
tokens/s
121
tokens/s
102
ms
pp2048+tg768
21845
tokens/s
117
tokens/s
102
ms
pp1024+tg1024
23831
tokens/s
126
tokens/s
51
ms
pp1280+tg3072
21592
tokens/s
108
tokens/s
67
ms
pp384+tg1152
20579
tokens/s
130
tokens/s
27
ms
pp64+tg1024
4492
tokens/s
131
tokens/s
22
ms
pp16+tg1536
1216
tokens/s
131
tokens/s
20
ms