TEST #1904 RESULTS
12/03/2025 - 8:30 PM
ACCELERATOR
MODEL
40.9
tokens/s
generation
645
ms
time to first token
2153
tokens/s
prompt
515
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i9-14900HX (alderlake)
RAM
95.7GB
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
2592
tokens/s
41.9
tokens/s
419
ms
pp4096+tg256
1799
tokens/s
39.4
tokens/s
2.30
sec
pp2048+tg256
2255
tokens/s
41.4
tokens/s
932
ms
pp2048+tg768
2260
tokens/s
41.1
tokens/s
930
ms
pp1024+tg1024
2592
tokens/s
39.7
tokens/s
419
ms
pp1280+tg3072
2509
tokens/s
39.8
tokens/s
537
ms
pp384+tg1152
3071
tokens/s
41.7
tokens/s
149
ms
pp64+tg1024
1821
tokens/s
40.9
tokens/s
59
ms
pp16+tg1536
476
tokens/s
41.8
tokens/s
58
ms