TEST #1055 RESULTS
06/14/2025 - 10:54 PM
ACCELERATOR
MODEL
219
tokens/s
generation
166
ms
time to first token
9424
tokens/s
prompt
2317
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5950X 16-Core Processor (znver3)
RAM
62.7GB
OS
Linux
Kernel Release
6.12.24-Unraid
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sat May 3 00:12:52 PDT 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
11637
tokens/s
227
tokens/s
92
ms
pp4096+tg256
6193
tokens/s
195
tokens/s
667
ms
pp2048+tg256
9005
tokens/s
214
tokens/s
232
ms
pp2048+tg768
8999
tokens/s
212
tokens/s
232
ms
pp1024+tg1024
11639
tokens/s
222
tokens/s
92
ms
pp1280+tg3072
10945
tokens/s
208
tokens/s
121
ms
pp384+tg1152
16029
tokens/s
228
tokens/s
28
ms
pp64+tg1024
8992
tokens/s
234
tokens/s
11
ms
pp16+tg1536
1373
tokens/s
231
tokens/s
16
ms