TEST #999 RESULTS
06/04/2025 - 8:15 PM
ACCELERATOR
MODEL
133
tokens/s
generation
284
ms
time to first token
4439
tokens/s
prompt
1276
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 5700X 8-Core Processor (znver3)
RAM
31.3GB
OS
Linux
Kernel Release
6.14.9-300.fc42.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Thu May 29 14:27:53 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
5982
tokens/s
163
tokens/s
178
ms
pp4096+tg256
4192
tokens/s
39.5
tokens/s
1.00
sec
pp2048+tg256
5111
tokens/s
114
tokens/s
409
ms
pp2048+tg768
5182
tokens/s
107
tokens/s
404
ms
pp1024+tg1024
5593
tokens/s
138
tokens/s
189
ms
pp1280+tg3072
5497
tokens/s
88.1
tokens/s
240
ms
pp384+tg1152
5638
tokens/s
169
tokens/s
73
ms
pp64+tg1024
1518
tokens/s
198
tokens/s
46
ms
pp16+tg1536
1238
tokens/s
180
tokens/s
18
ms