TEST #2088 RESULTS
01/03/2026 - 7:17 PM
ACCELERATOR
MODEL
45.5
tokens/s
generation
890
ms
time to first token
1439
tokens/s
prompt
419
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
1748
tokens/s
49.4
tokens/s
606
ms
pp4096+tg256
1386
tokens/s
42.4
tokens/s
2.98
sec
pp2048+tg256
1596
tokens/s
46.4
tokens/s
1.30
sec
pp2048+tg768
1588
tokens/s
46.1
tokens/s
1.31
sec
pp1024+tg1024
1710
tokens/s
47.7
tokens/s
619
ms
pp1280+tg3072
1645
tokens/s
42.7
tokens/s
799
ms
pp384+tg1152
1589
tokens/s
45.4
tokens/s
263
ms
pp64+tg1024
1234
tokens/s
45.4
tokens/s
75
ms
pp16+tg1536
456
tokens/s
44.3
tokens/s
56
ms