TEST #2257 RESULTS
01/12/2026 - 4:23 PM
ACCELERATOR
MODEL
87.8
tokens/s
generation
179
ms
time to first token
7272
tokens/s
prompt
1529
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
10119
tokens/s
96.7
tokens/s
111
ms
pp4096+tg256
6896
tokens/s
92.4
tokens/s
605
ms
pp2048+tg256
8502
tokens/s
93.6
tokens/s
253
ms
pp2048+tg768
8711
tokens/s
93.8
tokens/s
247
ms
pp1024+tg1024
10008
tokens/s
93.5
tokens/s
113
ms
pp1280+tg3072
9093
tokens/s
81.1
tokens/s
152
ms
pp384+tg1152
8590
tokens/s
79.0
tokens/s
56
ms
pp64+tg1024
2671
tokens/s
80.2
tokens/s
37
ms
pp16+tg1536
856
tokens/s
80.2
tokens/s
33
ms