TEST #3212 RESULTS
03/29/2026 - 6:45 AM
ACCELERATOR
MODEL
35.5
tokens/s
generation
1.84
sec
time to first token
793
tokens/s
prompt
248
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
12th Gen Intel Core i5-12500 (alderlake)
RAM
31.1GB
OS
Linux
Kernel Release
6.17.0-19-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #19~24.04.2-Ubuntu SMP PREEMPT_DYNAMIC Fri Mar 6 23:08:46 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
874
tokens/s
43.1
tokens/s
1.19
sec
pp4096+tg256
629
tokens/s
13.3
tokens/s
6.58
sec
pp2048+tg256
774
tokens/s
24.1
tokens/s
2.68
sec
pp2048+tg768
758
tokens/s
21.7
tokens/s
2.75
sec
pp1024+tg1024
835
tokens/s
32.3
tokens/s
1.25
sec
pp1280+tg3072
842
tokens/s
19.4
tokens/s
1.55
sec
pp384+tg1152
933
tokens/s
46.5
tokens/s
424
ms
pp64+tg1024
932
tokens/s
65.5
tokens/s
75
ms
pp16+tg1536
556
tokens/s
53.5
tokens/s
35
ms