TEST #1389 RESULTS
08/16/2025 - 9:26 AM
ACCELERATOR
MODEL
160
tokens/s
generation
281
ms
time to first token
5174
tokens/s
prompt
1433
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 5800HS with Radeon Graphics (znver3)
RAM
15GB
OS
Linux
Kernel Release
6.8.0-71-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #71-Ubuntu SMP PREEMPT_DYNAMIC Tue Jul 22 16:52:38 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
6091
tokens/s
173
tokens/s
174
ms
pp4096+tg256
3939
tokens/s
130
tokens/s
1.05
sec
pp2048+tg256
5108
tokens/s
153
tokens/s
408
ms
pp2048+tg768
5119
tokens/s
150
tokens/s
407
ms
pp1024+tg1024
6088
tokens/s
164
tokens/s
174
ms
pp1280+tg3072
5718
tokens/s
146
tokens/s
230
ms
pp384+tg1152
7619
tokens/s
171
tokens/s
56
ms
pp64+tg1024
5733
tokens/s
177
tokens/s
16
ms
pp16+tg1536
1156
tokens/s
174
tokens/s
19
ms