TEST #2264 RESULTS
01/12/2026 - 9:14 PM
ACCELERATOR
MODEL
33.3
tokens/s
generation
649
ms
time to first token
1955
tokens/s
prompt
465
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
2402
tokens/s
34.0
tokens/s
456
ms
pp4096+tg256
1964
tokens/s
30.5
tokens/s
2.12
sec
pp2048+tg256
2231
tokens/s
33.1
tokens/s
948
ms
pp2048+tg768
2235
tokens/s
32.2
tokens/s
946
ms
pp1024+tg1024
2406
tokens/s
33.8
tokens/s
455
ms
pp1280+tg3072
2316
tokens/s
32.0
tokens/s
581
ms
pp384+tg1152
2442
tokens/s
34.5
tokens/s
187
ms
pp64+tg1024
1196
tokens/s
35.0
tokens/s
81
ms
pp16+tg1536
398
tokens/s
34.5
tokens/s
67
ms