TEST #489 RESULTS
04/07/2025 - 11:17 AM
ACCELERATOR
MODEL
44.9
tokens/s
generation
289
ms
time to first token
4428
tokens/s
prompt
883
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 9950X3D 16-Core Processor
RAM
60.4GB
OS
Linux
Kernel Release
6.13.8-zen1-1-zen
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 ZEN SMP PREEMPT_DYNAMIC Sun, 23 Mar 2025 17:17:17 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
5676
tokens/s
51.6
tokens/s
200
ms
pp4096+tg256
4622
tokens/s
36.9
tokens/s
924
ms
pp2048+tg256
5288
tokens/s
44.9
tokens/s
410
ms
pp2048+tg768
5322
tokens/s
42.1
tokens/s
409
ms
pp1024+tg1024
5744
tokens/s
46.7
tokens/s
199
ms
pp1280+tg3072
5380
tokens/s
39.0
tokens/s
259
ms
pp384+tg1152
5757
tokens/s
46.0
tokens/s
87
ms
pp64+tg1024
1547
tokens/s
48.2
tokens/s
62
ms
pp16+tg1536
516
tokens/s
48.9
tokens/s
50
ms