TEST #860 RESULTS
05/13/2025 - 8:03 AM
ACCELERATOR
MODEL
60.6
tokens/s
generation
557
ms
time to first token
2427
tokens/s
prompt
641
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
62.7GB
OS
Linux
Kernel Release
6.8.0-59-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #61-Ubuntu SMP PREEMPT_DYNAMIC Fri Apr 11 23:16:11 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2822
tokens/s
62.9
tokens/s
379
ms
pp4096+tg256
2159
tokens/s
54.5
tokens/s
1.92
sec
pp2048+tg256
2544
tokens/s
59.6
tokens/s
822
ms
pp2048+tg768
2551
tokens/s
59.1
tokens/s
820
ms
pp1024+tg1024
2825
tokens/s
61.1
tokens/s
379
ms
pp1280+tg3072
2720
tokens/s
57.8
tokens/s
487
ms
pp384+tg1152
3188
tokens/s
62.8
tokens/s
136
ms
pp64+tg1024
2198
tokens/s
64.2
tokens/s
44
ms
pp16+tg1536
833
tokens/s
63.2
tokens/s
34
ms