TEST #101 RESULTS
03/28/2025 - 9:37 PM
ACCELERATOR
MODEL
212
tokens/s
generation
216
ms
time to first token
6350
tokens/s
prompt
1840
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E5-2690 0 @ 2.90GHz (sandybridge)
RAM
503.8GB
OS
Linux
Kernel Release
6.5.0-28-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #29~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Apr 4 14:39:20 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
8100
tokens/s
232
tokens/s
131
ms
pp4096+tg256
5496
tokens/s
163
tokens/s
751
ms
pp2048+tg256
6995
tokens/s
201
tokens/s
298
ms
pp2048+tg768
6980
tokens/s
195
tokens/s
298
ms
pp1024+tg1024
8023
tokens/s
216
tokens/s
132
ms
pp1280+tg3072
7578
tokens/s
186
tokens/s
173
ms
pp384+tg1152
8257
tokens/s
233
tokens/s
51
ms
pp64+tg1024
5539
tokens/s
246
tokens/s
15
ms
pp16+tg1536
179
tokens/s
238
tokens/s
95
ms