TEST #2124 RESULTS
01/04/2026 - 3:41 AM
ACCELERATOR
MODEL
45.1
tokens/s
generation
913
ms
time to first token
1410
tokens/s
prompt
411
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
1717
tokens/s
48.7
tokens/s
618
ms
pp4096+tg256
1362
tokens/s
42.0
tokens/s
3.03
sec
pp2048+tg256
1573
tokens/s
46.4
tokens/s
1.32
sec
pp2048+tg768
1571
tokens/s
45.8
tokens/s
1.33
sec
pp1024+tg1024
1671
tokens/s
46.6
tokens/s
634
ms
pp1280+tg3072
1475
tokens/s
41.5
tokens/s
889
ms
pp384+tg1152
1549
tokens/s
45.2
tokens/s
269
ms
pp64+tg1024
1319
tokens/s
45.2
tokens/s
70
ms
pp16+tg1536
449
tokens/s
44.9
tokens/s
57
ms