TEST #2260 RESULTS
01/12/2026 - 5:51 PM
ACCELERATOR
MODEL
91.0
tokens/s
generation
132
ms
time to first token
9623
tokens/s
prompt
1881
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
15576
tokens/s
109
tokens/s
75
ms
pp4096+tg256
10383
tokens/s
94.6
tokens/s
405
ms
pp2048+tg256
13350
tokens/s
105
tokens/s
166
ms
pp2048+tg768
13497
tokens/s
96.4
tokens/s
164
ms
pp1024+tg1024
10090
tokens/s
85.9
tokens/s
112
ms
pp1280+tg3072
9330
tokens/s
75.6
tokens/s
148
ms
pp384+tg1152
10385
tokens/s
81.2
tokens/s
49
ms
pp64+tg1024
3061
tokens/s
84.5
tokens/s
37
ms
pp16+tg1536
932
tokens/s
86.7
tokens/s
28
ms