TEST #2526 RESULTS
02/03/2026 - 10:03 PM
ACCELERATOR
MODEL
153
tokens/s
generation
298
ms
time to first token
4259
tokens/s
prompt
1299
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
5337
tokens/s
144
tokens/s
199
ms
pp4096+tg256
4019
tokens/s
106
tokens/s
1.03
sec
pp2048+tg256
4774
tokens/s
143
tokens/s
436
ms
pp2048+tg768
4823
tokens/s
138
tokens/s
432
ms
pp1024+tg1024
5265
tokens/s
161
tokens/s
200
ms
pp1280+tg3072
4998
tokens/s
132
tokens/s
262
ms
pp384+tg1152
5419
tokens/s
175
tokens/s
76
ms
pp64+tg1024
2700
tokens/s
195
tokens/s
28
ms
pp16+tg1536
997
tokens/s
187
tokens/s
21
ms