TEST #2229 RESULTS
01/10/2026 - 7:48 PM
ACCELERATOR
MODEL
100
tokens/s
generation
117
ms
time to first token
11177
tokens/s
prompt
2124
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
13th Gen Intel Core i5-1335U (alderlake)
RAM
63.2GB
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
18231
tokens/s
100.0
tokens/s
67
ms
pp4096+tg256
11634
tokens/s
105
tokens/s
361
ms
pp2048+tg256
15570
tokens/s
96.3
tokens/s
140
ms
pp2048+tg768
11178
tokens/s
94.8
tokens/s
196
ms
pp1024+tg1024
13815
tokens/s
98.6
tokens/s
87
ms
pp1280+tg3072
12797
tokens/s
95.4
tokens/s
112
ms
pp384+tg1152
12786
tokens/s
105
tokens/s
41
ms
pp64+tg1024
3480
tokens/s
104
tokens/s
27
ms
pp16+tg1536
1104
tokens/s
105
tokens/s
24
ms