TEST #676 RESULTS
04/10/2025 - 6:56 PM
ACCELERATOR
MODEL
68.2
tokens/s
generation
522
ms
time to first token
2355
tokens/s
prompt
675
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 Coder 7B Instruct GGUF - Q4_K - Medium
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
2943
tokens/s
73.0
tokens/s
362
ms
pp4096+tg256
2466
tokens/s
55.3
tokens/s
1.68
sec
pp2048+tg256
2731
tokens/s
68.0
tokens/s
765
ms
pp2048+tg768
2720
tokens/s
67.0
tokens/s
768
ms
pp1024+tg1024
2820
tokens/s
71.3
tokens/s
379
ms
pp1280+tg3072
2755
tokens/s
64.5
tokens/s
479
ms
pp384+tg1152
2367
tokens/s
71.6
tokens/s
177
ms
pp64+tg1024
1872
tokens/s
71.5
tokens/s
48
ms
pp16+tg1536
520
tokens/s
71.8
tokens/s
45
ms