TEST #1924 RESULTS
12/10/2025 - 1:12 PM
ACCELERATOR
MODEL
199
tokens/s
generation
180
ms
time to first token
7575
tokens/s
prompt
2030
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
13th Gen Intel Core i5-13500 (alderlake)
RAM
31.8GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
9397
tokens/s
203
tokens/s
114
ms
pp4096+tg256
6422
tokens/s
180
tokens/s
643
ms
pp2048+tg256
8127
tokens/s
203
tokens/s
258
ms
pp2048+tg768
8100
tokens/s
201
tokens/s
258
ms
pp1024+tg1024
9522
tokens/s
209
tokens/s
114
ms
pp1280+tg3072
9046
tokens/s
189
tokens/s
147
ms
pp384+tg1152
10446
tokens/s
200
tokens/s
42
ms
pp64+tg1024
6541
tokens/s
203
tokens/s
14
ms
pp16+tg1536
577
tokens/s
203
tokens/s
33
ms