TEST #1818 RESULTS
11/16/2025 - 4:10 PM
ACCELERATOR
MODEL
42.8
tokens/s
generation
696
ms
time to first token
1843
tokens/s
prompt
484
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
13th Gen Intel Core i5-13600KF (alderlake)
RAM
15.8GB
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
2218
tokens/s
44.2
tokens/s
484
ms
pp4096+tg256
1818
tokens/s
41.0
tokens/s
2.28
sec
pp2048+tg256
1954
tokens/s
43.3
tokens/s
1.07
sec
pp2048+tg768
2087
tokens/s
42.4
tokens/s
1.01
sec
pp1024+tg1024
2276
tokens/s
44.3
tokens/s
472
ms
pp1280+tg3072
2382
tokens/s
43.1
tokens/s
561
ms
pp384+tg1152
2240
tokens/s
44.1
tokens/s
194
ms
pp64+tg1024
1481
tokens/s
39.2
tokens/s
65
ms
pp16+tg1536
136
tokens/s
43.7
tokens/s
140
ms