TEST #466 RESULTS
04/07/2025 - 4:00 AM
ACCELERATOR
MODEL
191
tokens/s
generation
181
ms
time to first token
8762
tokens/s
prompt
2100
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen Threadripper PRO 3975WX 32-Cores (znver2)
RAM
251.5GB
OS
Linux
Kernel Release
6.8.0-52-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #53-Ubuntu SMP PREEMPT_DYNAMIC Sat Jan 11 00:06:25 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
10749
tokens/s
195
tokens/s
100
ms
pp4096+tg256
5716
tokens/s
170
tokens/s
722
ms
pp2048+tg256
8226
tokens/s
188
tokens/s
254
ms
pp2048+tg768
8219
tokens/s
186
tokens/s
254
ms
pp1024+tg1024
11472
tokens/s
196
tokens/s
94
ms
pp1280+tg3072
9547
tokens/s
181
tokens/s
139
ms
pp384+tg1152
15095
tokens/s
199
tokens/s
30
ms
pp64+tg1024
8742
tokens/s
204
tokens/s
12
ms
pp16+tg1536
1092
tokens/s
201
tokens/s
21
ms