TEST #2525 RESULTS
02/03/2026 - 10:02 PM
ACCELERATOR
MODEL
145
tokens/s
generation
306
ms
time to first token
4042
tokens/s
prompt
1242
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i7-6700K CPU @ 4.00GHz (skylake)
RAM
31.9GB
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
5083
tokens/s
142
tokens/s
208
ms
pp4096+tg256
3917
tokens/s
107
tokens/s
1.05
sec
pp2048+tg256
4723
tokens/s
140
tokens/s
441
ms
pp2048+tg768
4735
tokens/s
135
tokens/s
440
ms
pp1024+tg1024
5279
tokens/s
160
tokens/s
200
ms
pp1280+tg3072
4874
tokens/s
124
tokens/s
269
ms
pp384+tg1152
4509
tokens/s
160
tokens/s
91
ms
pp64+tg1024
2358
tokens/s
173
tokens/s
32
ms
pp16+tg1536
899
tokens/s
166
tokens/s
23
ms