TEST #2263 RESULTS
01/12/2026 - 9:09 PM
ACCELERATOR
MODEL
86.8
tokens/s
generation
176
ms
time to first token
7372
tokens/s
prompt
1539
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
10141
tokens/s
93.8
tokens/s
111
ms
pp4096+tg256
6914
tokens/s
92.8
tokens/s
603
ms
pp2048+tg256
8765
tokens/s
91.8
tokens/s
244
ms
pp2048+tg768
8723
tokens/s
92.6
tokens/s
245
ms
pp1024+tg1024
10127
tokens/s
95.6
tokens/s
111
ms
pp1280+tg3072
9396
tokens/s
75.6
tokens/s
146
ms
pp384+tg1152
8615
tokens/s
78.5
tokens/s
56
ms
pp64+tg1024
2864
tokens/s
80.5
tokens/s
33
ms
pp16+tg1536
806
tokens/s
80.0
tokens/s
31
ms