TEST #889 RESULTS
05/16/2025 - 7:31 PM
ACCELERATOR
MODEL
21.0
tokens/s
generation
2.61
sec
time to first token
540
tokens/s
prompt
163
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
11th Gen Intel Core i7-11850H @ 2.50GHz (tigerlake)
RAM
62.5GB
OS
Linux
Kernel Release
6.8.0-60-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #63-Ubuntu SMP PREEMPT_DYNAMIC Tue Apr 15 19:04:15 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
609
tokens/s
25.6
tokens/s
1.72
sec
pp4096+tg256
445
tokens/s
7.6
tokens/s
9.33
sec
pp2048+tg256
542
tokens/s
13.9
tokens/s
3.85
sec
pp2048+tg768
542
tokens/s
12.6
tokens/s
3.85
sec
pp1024+tg1024
609
tokens/s
18.8
tokens/s
1.72
sec
pp1280+tg3072
593
tokens/s
11.0
tokens/s
2.20
sec
pp384+tg1152
661
tokens/s
27.6
tokens/s
601
ms
pp64+tg1024
679
tokens/s
39.9
tokens/s
105
ms
pp16+tg1536
176
tokens/s
32.1
tokens/s
100
ms