TEST #598 RESULTS
04/08/2025 - 12:28 PM
ACCELERATOR
MODEL
114
tokens/s
generation
286
ms
time to first token
4979
tokens/s
prompt
1255
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
13th Gen Intel Core i5-13450HX (alderlake)
RAM
15.7GB
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
6579
tokens/s
106
tokens/s
166
ms
pp4096+tg256
3796
tokens/s
107
tokens/s
1.09
sec
pp2048+tg256
5288
tokens/s
112
tokens/s
397
ms
pp2048+tg768
5291
tokens/s
116
tokens/s
398
ms
pp1024+tg1024
6685
tokens/s
113
tokens/s
161
ms
pp1280+tg3072
6315
tokens/s
114
tokens/s
211
ms
pp384+tg1152
8902
tokens/s
118
tokens/s
50
ms
pp64+tg1024
1632
tokens/s
119
tokens/s
47
ms
pp16+tg1536
326
tokens/s
118
tokens/s
58
ms