TEST #3298 RESULTS
04/12/2026 - 3:04 PM
ACCELERATOR
MODEL
40.3
tokens/s
generation
847
ms
time to first token
1591
tokens/s
prompt
423
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
13th Gen Intel Core i7-13700HX (alderlake)
RAM
31.7GB
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
1851
tokens/s
40.1
tokens/s
578
ms
pp4096+tg256
1429
tokens/s
37.3
tokens/s
2.89
sec
pp2048+tg256
1673
tokens/s
40.5
tokens/s
1.25
sec
pp2048+tg768
1671
tokens/s
40.0
tokens/s
1.25
sec
pp1024+tg1024
1850
tokens/s
41.1
tokens/s
578
ms
pp1280+tg3072
1808
tokens/s
39.4
tokens/s
732
ms
pp384+tg1152
2121
tokens/s
42.0
tokens/s
204
ms
pp64+tg1024
1545
tokens/s
41.2
tokens/s
65
ms
pp16+tg1536
372
tokens/s
41.1
tokens/s
70
ms