TEST #1001 RESULTS
06/04/2025 - 8:27 PM
ACCELERATOR
MODEL
45.3
tokens/s
generation
1.42
sec
time to first token
885
tokens/s
prompt
305
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 5700X 8-Core Processor (znver3)
RAM
31.3GB
OS
Linux
Kernel Release
6.14.9-300.fc42.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Thu May 29 14:27:53 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1061
tokens/s
55.9
tokens/s
984
ms
pp4096+tg256
858
tokens/s
12.5
tokens/s
4.85
sec
pp2048+tg256
1006
tokens/s
40.1
tokens/s
2.06
sec
pp2048+tg768
1010
tokens/s
38.7
tokens/s
2.05
sec
pp1024+tg1024
1089
tokens/s
47.7
tokens/s
958
ms
pp1280+tg3072
1046
tokens/s
30.7
tokens/s
1.24
sec
pp384+tg1152
1089
tokens/s
57.2
tokens/s
367
ms
pp64+tg1024
366
tokens/s
64.8
tokens/s
188
ms
pp16+tg1536
440
tokens/s
60.3
tokens/s
49
ms