TEST #2230 RESULTS
01/10/2026 - 8:30 PM
ACCELERATOR
MODEL
48.6
tokens/s
generation
313
ms
time to first token
4023
tokens/s
prompt
856
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
13th Gen Intel Core i5-1335U (alderlake)
RAM
63.2GB
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
5349
tokens/s
54.8
tokens/s
210
ms
pp4096+tg256
4146
tokens/s
46.6
tokens/s
1.01
sec
pp2048+tg256
4838
tokens/s
49.3
tokens/s
444
ms
pp2048+tg768
4843
tokens/s
51.1
tokens/s
441
ms
pp1024+tg1024
5317
tokens/s
49.4
tokens/s
211
ms
pp1280+tg3072
5056
tokens/s
43.3
tokens/s
275
ms
pp384+tg1152
4252
tokens/s
46.6
tokens/s
114
ms
pp64+tg1024
1888
tokens/s
48.3
tokens/s
54
ms
pp16+tg1536
515
tokens/s
48.4
tokens/s
54
ms