TEST #325 RESULTS
04/06/2025 - 12:23 AM
ACCELERATOR
MODEL
113
tokens/s
generation
296
ms
time to first token
5176
tokens/s
prompt
1256
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
125.7GB
OS
Linux
Kernel Release
6.13.9-200.fc41.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sat Mar 29 01:29:31 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
6820
tokens/s
142
tokens/s
157
ms
pp4096+tg256
3483
tokens/s
24.4
tokens/s
1.22
sec
pp2048+tg256
5060
tokens/s
98.6
tokens/s
415
ms
pp2048+tg768
5075
tokens/s
92.2
tokens/s
413
ms
pp1024+tg1024
6577
tokens/s
121
tokens/s
163
ms
pp1280+tg3072
6328
tokens/s
68.2
tokens/s
210
ms
pp384+tg1152
7678
tokens/s
147
tokens/s
55
ms
pp64+tg1024
3588
tokens/s
171
tokens/s
23
ms
pp16+tg1536
1978
tokens/s
156
tokens/s
13
ms