TEST #335 RESULTS
04/06/2025 - 1:17 AM
ACCELERATOR
MODEL
34.9
tokens/s
generation
1.27
sec
time to first token
1157
tokens/s
prompt
317
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q5_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5950X 16-Core Processor (znver3)
RAM
125.7GB
OS
Linux
Kernel Release
6.13.9-200.fc41.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sat Mar 29 01:29:31 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1297
tokens/s
41.4
tokens/s
813
ms
pp4096+tg256
850
tokens/s
6.7
tokens/s
4.96
sec
pp2048+tg256
1184
tokens/s
33.2
tokens/s
1.76
sec
pp2048+tg768
1186
tokens/s
31.5
tokens/s
1.76
sec
pp1024+tg1024
1415
tokens/s
38.1
tokens/s
747
ms
pp1280+tg3072
1360
tokens/s
22.3
tokens/s
966
ms
pp384+tg1152
1613
tokens/s
44.1
tokens/s
258
ms
pp64+tg1024
953
tokens/s
49.7
tokens/s
85
ms
pp16+tg1536
551
tokens/s
46.9
tokens/s
46
ms