TEST #1275 RESULTS
07/30/2025 - 3:10 PM
ACCELERATOR
MODEL
53.8
tokens/s
generation
5.95
sec
time to first token
263
tokens/s
prompt
133
LocalScore
HOW YOU STACK UP
Explore All Results.. - Q4_0
SYSTEM
CPU
AMD Ryzen 7 5700G with Radeon Graphics (znver3)
RAM
58.7GB
OS
Linux
Kernel Release
6.12.34-6.12-alt1
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Tue Jun 24 14:31:35 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
270
tokens/s
57.1
tokens/s
3.81
sec
pp4096+tg256
186
tokens/s
44.8
tokens/s
22.01
sec
pp2048+tg256
236
tokens/s
51.9
tokens/s
8.69
sec
pp2048+tg768
236
tokens/s
51.2
tokens/s
8.71
sec
pp1024+tg1024
267
tokens/s
54.7
tokens/s
3.85
sec
pp1280+tg3072
263
tokens/s
49.2
tokens/s
4.88
sec
pp384+tg1152
302
tokens/s
57.3
tokens/s
1.29
sec
pp64+tg1024
317
tokens/s
59.4
tokens/s
220
ms
pp16+tg1536
286
tokens/s
58.2
tokens/s
71
ms