TEST #1468 RESULTS
09/02/2025 - 12:45 AM
ACCELERATOR
MODEL
13.3
tokens/s
generation
39.15
sec
time to first token
37
tokens/s
prompt
23
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-5300U CPU @ 2.30GHz (broadwell)
RAM
9.4GB
OS
Linux
Kernel Release
6.14.8-2-pve
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC PMX 6.14.8-2 (2025-07-22T10:04Z)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
43
tokens/s
16.7
tokens/s
24.09
sec
pp4096+tg256
34
tokens/s
9.2
tokens/s
121.66
sec
pp2048+tg256
38
tokens/s
13.6
tokens/s
54.28
sec
pp2048+tg768
39
tokens/s
12.5
tokens/s
53.14
sec
pp1024+tg1024
41
tokens/s
14.1
tokens/s
25.22
sec
pp1280+tg3072
21
tokens/s
10.0
tokens/s
62.88
sec
pp384+tg1152
43
tokens/s
13.9
tokens/s
9.08
sec
pp64+tg1024
46
tokens/s
15.1
tokens/s
1.46
sec
pp16+tg1536
35
tokens/s
14.9
tokens/s
535
ms