TEST #1816 RESULTS
11/16/2025 - 2:59 PM
ACCELERATOR
MODEL
42.6
tokens/s
generation
1.08
sec
time to first token
1279
tokens/s
prompt
370
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
13th Gen Intel Core i5-13500 (alderlake)
RAM
31.8GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1500
tokens/s
43.1
tokens/s
705
ms
pp4096+tg256
1041
tokens/s
28.3
tokens/s
3.95
sec
pp2048+tg256
1321
tokens/s
43.7
tokens/s
1.58
sec
pp2048+tg768
1490
tokens/s
44.4
tokens/s
1.40
sec
pp1024+tg1024
1656
tokens/s
46.1
tokens/s
639
ms
pp1280+tg3072
1283
tokens/s
37.3
tokens/s
1.03
sec
pp384+tg1152
1470
tokens/s
46.9
tokens/s
288
ms
pp64+tg1024
1297
tokens/s
47.2
tokens/s
70
ms
pp16+tg1536
448
tokens/s
46.6
tokens/s
55
ms