TEST #1598 RESULTS
10/07/2025 - 12:52 AM
ACCELERATOR
MODEL
128
tokens/s
generation
287
ms
time to first token
4640
tokens/s
prompt
1275
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 3700X 8-Core Processor (znver2)
RAM
62.8GB
OS
Linux
Kernel Release
6.6.87.2-microsoft-standard-WSL2
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Thu Jun 5 18:30:46 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
5808
tokens/s
139
tokens/s
183
ms
pp4096+tg256
4030
tokens/s
98.5
tokens/s
1.03
sec
pp2048+tg256
5071
tokens/s
124
tokens/s
412
ms
pp2048+tg768
5083
tokens/s
120
tokens/s
411
ms
pp1024+tg1024
5813
tokens/s
132
tokens/s
183
ms
pp1280+tg3072
5462
tokens/s
114
tokens/s
242
ms
pp384+tg1152
6230
tokens/s
141
tokens/s
69
ms
pp64+tg1024
3637
tokens/s
144
tokens/s
25
ms
pp16+tg1536
627
tokens/s
142
tokens/s
33
ms