TEST #1182 RESULTS
07/05/2025 - 4:32 AM
ACCELERATOR
MODEL
137
tokens/s
generation
104
ms
time to first token
12969
tokens/s
prompt
2571
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 7800X3D 8-Core Processor (znver4)
RAM
61.9GB
OS
Linux
Kernel Release
6.15.4-200.fc42.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Fri Jun 27 15:32:46 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
16299
tokens/s
155
tokens/s
69
ms
pp4096+tg256
11515
tokens/s
112
tokens/s
365
ms
pp2048+tg256
14917
tokens/s
135
tokens/s
145
ms
pp2048+tg768
14882
tokens/s
130
tokens/s
145
ms
pp1024+tg1024
17088
tokens/s
142
tokens/s
67
ms
pp1280+tg3072
16064
tokens/s
120
tokens/s
87
ms
pp384+tg1152
18840
tokens/s
143
tokens/s
28
ms
pp64+tg1024
5534
tokens/s
148
tokens/s
18
ms
pp16+tg1536
1577
tokens/s
147
tokens/s
16
ms