TEST #1088 RESULTS
06/23/2025 - 2:15 AM
ACCELERATOR
MODEL
41.2
tokens/s
generation
793
ms
time to first token
1708
tokens/s
prompt
446
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 5600 6-Core Processor (znver3)
RAM
31.9GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1984
tokens/s
41.7
tokens/s
540
ms
pp4096+tg256
1516
tokens/s
38.8
tokens/s
2.73
sec
pp2048+tg256
1793
tokens/s
41.3
tokens/s
1.17
sec
pp2048+tg768
1801
tokens/s
40.9
tokens/s
1.16
sec
pp1024+tg1024
1976
tokens/s
41.4
tokens/s
542
ms
pp1280+tg3072
1935
tokens/s
40.4
tokens/s
686
ms
pp384+tg1152
2238
tokens/s
42.1
tokens/s
195
ms
pp64+tg1024
1654
tokens/s
42.2
tokens/s
62
ms
pp16+tg1536
475
tokens/s
42.1
tokens/s
57
ms