TEST #588 RESULTS
04/08/2025 - 11:23 AM
ACCELERATOR
MODEL
160
tokens/s
generation
468
ms
time to first token
2665
tokens/s
prompt
969
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
3191
tokens/s
184
tokens/s
326
ms
pp4096+tg256
2650
tokens/s
97.7
tokens/s
1.56
sec
pp2048+tg256
2913
tokens/s
140
tokens/s
710
ms
pp2048+tg768
2978
tokens/s
132
tokens/s
695
ms
pp1024+tg1024
3198
tokens/s
160
tokens/s
326
ms
pp1280+tg3072
3149
tokens/s
123
tokens/s
412
ms
pp384+tg1152
3154
tokens/s
189
tokens/s
127
ms
pp64+tg1024
1832
tokens/s
213
tokens/s
39
ms
pp16+tg1536
921
tokens/s
200
tokens/s
21
ms