TEST #600 RESULTS
04/08/2025 - 12:40 PM
ACCELERATOR
MODEL
165
tokens/s
generation
455
ms
time to first token
2750
tokens/s
prompt
999
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
6.14.1-1-cachyos
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Tue, 08 Apr 2025 06:33:52 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3297
tokens/s
190
tokens/s
316
ms
pp4096+tg256
2716
tokens/s
101
tokens/s
1.52
sec
pp2048+tg256
3018
tokens/s
144
tokens/s
685
ms
pp2048+tg768
3056
tokens/s
136
tokens/s
677
ms
pp1024+tg1024
3283
tokens/s
166
tokens/s
317
ms
pp1280+tg3072
3235
tokens/s
127
tokens/s
401
ms
pp384+tg1152
3242
tokens/s
195
tokens/s
123
ms
pp64+tg1024
1963
tokens/s
221
tokens/s
37
ms
pp16+tg1536
943
tokens/s
206
tokens/s
21
ms