TEST #3213 RESULTS
03/29/2026 - 10:04 AM
ACCELERATOR
MODEL
35.3
tokens/s
generation
1.80
sec
time to first token
793
tokens/s
prompt
250
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
873
tokens/s
43.1
tokens/s
1.20
sec
pp4096+tg256
645
tokens/s
13.6
tokens/s
6.43
sec
pp2048+tg256
780
tokens/s
24.4
tokens/s
2.66
sec
pp2048+tg768
780
tokens/s
21.9
tokens/s
2.66
sec
pp1024+tg1024
889
tokens/s
32.4
tokens/s
1.17
sec
pp1280+tg3072
838
tokens/s
18.7
tokens/s
1.55
sec
pp384+tg1152
927
tokens/s
45.4
tokens/s
428
ms
pp64+tg1024
895
tokens/s
65.5
tokens/s
78
ms
pp16+tg1536
514
tokens/s
53.0
tokens/s
37
ms