TEST #2279 RESULTS
01/13/2026 - 8:24 PM
ACCELERATOR
MODEL
26.5
tokens/s
generation
10.78
sec
time to first token
124
tokens/s
prompt
67
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
12th Gen Intel Core i7-1260P (alderlake)
RAM
35.2GB
OS
Linux
Kernel Release
6.12.57+deb13-amd64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Debian 6.12.57-1 (2025-11-05)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
180
tokens/s
38.2
tokens/s
5.72
sec
pp4096+tg256
126
tokens/s
20.7
tokens/s
32.67
sec
pp2048+tg256
124
tokens/s
23.8
tokens/s
16.51
sec
pp2048+tg768
119
tokens/s
27.6
tokens/s
17.30
sec
pp1024+tg1024
110
tokens/s
27.1
tokens/s
9.33
sec
pp1280+tg3072
117
tokens/s
23.9
tokens/s
10.98
sec
pp384+tg1152
103
tokens/s
26.9
tokens/s
3.75
sec
pp64+tg1024
121
tokens/s
25.6
tokens/s
564
ms
pp16+tg1536
114
tokens/s
25.0
tokens/s
164
ms