TEST #507 RESULTS
04/07/2025 - 6:24 PM
ACCELERATOR
MODEL
189
tokens/s
generation
103
ms
time to first token
14676
tokens/s
prompt
2997
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
13th Gen Intel Core i7-13700K (alderlake)
RAM
63.7GB
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
20080
tokens/s
224
tokens/s
56
ms
pp4096+tg256
10353
tokens/s
192
tokens/s
401
ms
pp2048+tg256
14983
tokens/s
187
tokens/s
142
ms
pp2048+tg768
14729
tokens/s
183
tokens/s
145
ms
pp1024+tg1024
19615
tokens/s
189
tokens/s
58
ms
pp1280+tg3072
17840
tokens/s
180
tokens/s
77
ms
pp384+tg1152
23600
tokens/s
181
tokens/s
22
ms
pp64+tg1024
8655
tokens/s
179
tokens/s
13
ms
pp16+tg1536
2228
tokens/s
183
tokens/s
13
ms