TEST #633 RESULTS
04/09/2025 - 8:39 AM
ACCELERATOR
MODEL
181
tokens/s
generation
161
ms
time to first token
8206
tokens/s
prompt
2099
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
13th Gen Intel Core i9-13980HX (alderlake)
RAM
191.7GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
12845
tokens/s
181
tokens/s
86
ms
pp4096+tg256
7544
tokens/s
175
tokens/s
549
ms
pp2048+tg256
9796
tokens/s
180
tokens/s
214
ms
pp2048+tg768
8946
tokens/s
189
tokens/s
235
ms
pp1024+tg1024
6586
tokens/s
185
tokens/s
161
ms
pp1280+tg3072
12481
tokens/s
182
tokens/s
109
ms
pp384+tg1152
6348
tokens/s
179
tokens/s
65
ms
pp64+tg1024
7091
tokens/s
181
tokens/s
14
ms
pp16+tg1536
2220
tokens/s
180
tokens/s
14
ms