TEST #2592 RESULTS
02/10/2026 - 5:17 PM
ACCELERATOR
MODEL
204
tokens/s
generation
162
ms
time to first token
8600
tokens/s
prompt
2214
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
12th Gen Intel Core i7-12700KF (alderlake)
RAM
63.9GB
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
10685
tokens/s
208
tokens/s
101
ms
pp4096+tg256
6831
tokens/s
187
tokens/s
605
ms
pp2048+tg256
9221
tokens/s
206
tokens/s
227
ms
pp2048+tg768
9209
tokens/s
209
tokens/s
227
ms
pp1024+tg1024
10996
tokens/s
203
tokens/s
99
ms
pp1280+tg3072
10372
tokens/s
203
tokens/s
129
ms
pp384+tg1152
11997
tokens/s
198
tokens/s
37
ms
pp64+tg1024
6734
tokens/s
211
tokens/s
14
ms
pp16+tg1536
1352
tokens/s
212
tokens/s
16
ms