TEST #3870 RESULTS
07/06/2026 - 6:41 PM
ACCELERATOR
MODEL
50.2
tokens/s
generation
5.28
sec
time to first token
266
tokens/s
prompt
136
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
13th Gen Intel Core i7-13700K (alderlake)
RAM
63.7GB
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
303
tokens/s
49.4
tokens/s
3.40
sec
pp4096+tg256
233
tokens/s
44.9
tokens/s
17.58
sec
pp2048+tg256
248
tokens/s
49.8
tokens/s
8.28
sec
pp2048+tg768
255
tokens/s
49.3
tokens/s
8.04
sec
pp1024+tg1024
272
tokens/s
51.3
tokens/s
3.78
sec
pp1280+tg3072
273
tokens/s
47.2
tokens/s
4.71
sec
pp384+tg1152
274
tokens/s
52.4
tokens/s
1.42
sec
pp64+tg1024
317
tokens/s
54.0
tokens/s
219
ms
pp16+tg1536
220
tokens/s
53.4
tokens/s
91
ms