TEST #3988 RESULTS
08/03/2026 - 12:04 PM
ACCELERATOR
MODEL
25.7
tokens/s
generation
10.68
sec
time to first token
135
tokens/s
prompt
69
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i7-7700K CPU @ 4.20GHz (skylake)
RAM
31GB
OS
Linux
Kernel Release
7.0.6-2-pve
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC PMX 7.0.6-2 (2026-05-29T11:08Z)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
156
tokens/s
27.9
tokens/s
6.62
sec
pp4096+tg256
113
tokens/s
21.4
tokens/s
36.19
sec
pp2048+tg256
127
tokens/s
25.1
tokens/s
16.19
sec
pp2048+tg768
125
tokens/s
24.3
tokens/s
16.45
sec
pp1024+tg1024
137
tokens/s
26.1
tokens/s
7.53
sec
pp1280+tg3072
132
tokens/s
23.5
tokens/s
9.70
sec
pp384+tg1152
140
tokens/s
27.4
tokens/s
2.77
sec
pp64+tg1024
140
tokens/s
28.2
tokens/s
489
ms
pp16+tg1536
144
tokens/s
27.7
tokens/s
145
ms