TEST #1132 RESULTS
06/27/2025 - 1:33 AM
ACCELERATOR
MODEL
185
tokens/s
generation
172
ms
time to first token
9351
tokens/s
prompt
2156
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i9-14900KS (alderlake)
RAM
244.2GB
OS
Linux
Kernel Release
6.14.0-22-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #22-Ubuntu SMP PREEMPT_DYNAMIC Wed May 21 15:01:51 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
11814
tokens/s
192
tokens/s
92
ms
pp4096+tg256
5870
tokens/s
163
tokens/s
704
ms
pp2048+tg256
8645
tokens/s
183
tokens/s
243
ms
pp2048+tg768
8644
tokens/s
180
tokens/s
243
ms
pp1024+tg1024
11637
tokens/s
189
tokens/s
93
ms
pp1280+tg3072
10676
tokens/s
174
tokens/s
125
ms
pp384+tg1152
16451
tokens/s
193
tokens/s
28
ms
pp64+tg1024
7925
tokens/s
197
tokens/s
13
ms
pp16+tg1536
2494
tokens/s
194
tokens/s
11
ms