TEST #681 RESULTS
04/10/2025 - 7:31 PM
ACCELERATOR
MODEL
54.2
tokens/s
generation
939
ms
time to first token
1459
tokens/s
prompt
438
LocalScore
HOW YOU STACK UP
Explore All ResultsDeepSeek R1 Distill Qwen 7B - Q6_K
SYSTEM
CPU
AMD Ryzen 5 5600X 6-Core Processor (znver3)
RAM
95.9GB
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
1776
tokens/s
57.1
tokens/s
595
ms
pp4096+tg256
2069
tokens/s
41.8
tokens/s
2.00
sec
pp2048+tg256
668
tokens/s
42.8
tokens/s
3.08
sec
pp2048+tg768
1911
tokens/s
54.7
tokens/s
1.09
sec
pp1024+tg1024
1823
tokens/s
58.5
tokens/s
579
ms
pp1280+tg3072
2019
tokens/s
54.0
tokens/s
651
ms
pp384+tg1152
1252
tokens/s
59.3
tokens/s
324
ms
pp64+tg1024
1168
tokens/s
59.7
tokens/s
71
ms
pp16+tg1536
440
tokens/s
59.6
tokens/s
53
ms