TEST #2299 RESULTS
01/15/2026 - 2:06 PM
ACCELERATOR
MODEL
103
tokens/s
generation
177
ms
time to first token
8234
tokens/s
prompt
1685
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 3600 6-Core Processor (znver2)
RAM
7.7GB
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
10912
tokens/s
124
tokens/s
102
ms
pp4096+tg256
7162
tokens/s
121
tokens/s
579
ms
pp2048+tg256
8787
tokens/s
78.3
tokens/s
240
ms
pp2048+tg768
9017
tokens/s
83.2
tokens/s
240
ms
pp1024+tg1024
10766
tokens/s
87.3
tokens/s
141
ms
pp1280+tg3072
9937
tokens/s
97.8
tokens/s
181
ms
pp384+tg1152
11555
tokens/s
124
tokens/s
41
ms
pp64+tg1024
4711
tokens/s
92.8
tokens/s
21
ms
pp16+tg1536
1261
tokens/s
117
tokens/s
47
ms