TEST #2087 RESULTS
01/03/2026 - 7:13 PM
ACCELERATOR
MODEL
45.2
tokens/s
generation
899
ms
time to first token
1450
tokens/s
prompt
418
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
11th Gen Intel Core i7-11800H @ 2.30GHz (tigerlake)
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
1732
tokens/s
48.5
tokens/s
612
ms
pp4096+tg256
1375
tokens/s
42.4
tokens/s
3.00
sec
pp2048+tg256
1580
tokens/s
46.8
tokens/s
1.32
sec
pp2048+tg768
1578
tokens/s
46.0
tokens/s
1.32
sec
pp1024+tg1024
1702
tokens/s
46.0
tokens/s
623
ms
pp1280+tg3072
1538
tokens/s
42.0
tokens/s
853
ms
pp384+tg1152
1747
tokens/s
44.1
tokens/s
242
ms
pp64+tg1024
1368
tokens/s
45.1
tokens/s
68
ms
pp16+tg1536
428
tokens/s
45.5
tokens/s
59
ms