TEST #1601 RESULTS
10/07/2025 - 2:51 AM
ACCELERATOR
MODEL
41.0
tokens/s
generation
1.13
sec
time to first token
1159
tokens/s
prompt
348
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 Coder 7B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 3700X 8-Core Processor (znver2)
RAM
62.8GB
OS
Linux
Kernel Release
6.6.87.2-microsoft-standard-WSL2
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Thu Jun 5 18:30:46 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1253
tokens/s
46.2
tokens/s
839
ms
pp4096+tg256
1054
tokens/s
30.7
tokens/s
3.94
sec
pp2048+tg256
1323
tokens/s
38.6
tokens/s
1.57
sec
pp2048+tg768
1319
tokens/s
37.4
tokens/s
1.58
sec
pp1024+tg1024
1374
tokens/s
43.5
tokens/s
767
ms
pp1280+tg3072
1339
tokens/s
36.3
tokens/s
978
ms
pp384+tg1152
1392
tokens/s
45.3
tokens/s
298
ms
pp64+tg1024
1080
tokens/s
45.7
tokens/s
81
ms
pp16+tg1536
297
tokens/s
45.6
tokens/s
75
ms