TEST #2282 RESULTS
01/14/2026 - 1:11 PM
ACCELERATOR
MODEL
98.3
tokens/s
generation
131
ms
time to first token
9569
tokens/s
prompt
1927
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
18315
tokens/s
154
tokens/s
63
ms
pp4096+tg256
11946
tokens/s
96.7
tokens/s
351
ms
pp2048+tg256
10821
tokens/s
108
tokens/s
200
ms
pp2048+tg768
11681
tokens/s
104
tokens/s
184
ms
pp1024+tg1024
13266
tokens/s
90.8
tokens/s
88
ms
pp1280+tg3072
8002
tokens/s
75.8
tokens/s
174
ms
pp384+tg1152
8564
tokens/s
82.7
tokens/s
58
ms
pp64+tg1024
2677
tokens/s
87.6
tokens/s
35
ms
pp16+tg1536
847
tokens/s
84.7
tokens/s
30
ms