TEST #2283 RESULTS
01/14/2026 - 1:16 PM
ACCELERATOR
MODEL
35.4
tokens/s
generation
646
ms
time to first token
1961
tokens/s
prompt
476
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
2417
tokens/s
36.1
tokens/s
453
ms
pp4096+tg256
1964
tokens/s
32.9
tokens/s
2.12
sec
pp2048+tg256
2253
tokens/s
35.4
tokens/s
937
ms
pp2048+tg768
2240
tokens/s
35.0
tokens/s
944
ms
pp1024+tg1024
2429
tokens/s
36.3
tokens/s
449
ms
pp1280+tg3072
2328
tokens/s
34.5
tokens/s
577
ms
pp384+tg1152
2387
tokens/s
36.0
tokens/s
190
ms
pp64+tg1024
1214
tokens/s
36.4
tokens/s
79
ms
pp16+tg1536
417
tokens/s
36.5
tokens/s
65
ms