TEST #683 RESULTS
04/10/2025 - 7:38 PM
ACCELERATOR
MODEL
57.1
tokens/s
generation
568
ms
time to first token
2136
tokens/s
prompt
599
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5.1 Coder 7B Instruct - 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
2634
tokens/s
60.5
tokens/s
406
ms
pp4096+tg256
2313
tokens/s
47.8
tokens/s
1.79
sec
pp2048+tg256
2532
tokens/s
57.0
tokens/s
826
ms
pp2048+tg768
2523
tokens/s
56.1
tokens/s
830
ms
pp1024+tg1024
2615
tokens/s
58.8
tokens/s
408
ms
pp1280+tg3072
2528
tokens/s
54.1
tokens/s
524
ms
pp384+tg1152
1901
tokens/s
59.6
tokens/s
220
ms
pp64+tg1024
1662
tokens/s
59.9
tokens/s
55
ms
pp16+tg1536
519
tokens/s
59.7
tokens/s
48
ms