TEST #994 RESULTS
06/04/2025 - 10:47 AM
ACCELERATOR
MODEL
29.9
tokens/s
generation
7.95
sec
time to first token
187
tokens/s
prompt
89
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 4800H with Radeon Graphics (znver2)
RAM
15GB
OS
Linux
Kernel Release
6.9.11-100.fc39.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Thu Jul 25 18:16:24 UTC 2024
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
194
tokens/s
32.2
tokens/s
5.32
sec
pp4096+tg256
146
tokens/s
25.7
tokens/s
28.17
sec
pp2048+tg256
174
tokens/s
29.6
tokens/s
11.82
sec
pp2048+tg768
175
tokens/s
28.9
tokens/s
11.73
sec
pp1024+tg1024
194
tokens/s
30.6
tokens/s
5.32
sec
pp1280+tg3072
187
tokens/s
27.5
tokens/s
6.87
sec
pp384+tg1152
210
tokens/s
31.3
tokens/s
1.85
sec
pp64+tg1024
200
tokens/s
32.2
tokens/s
353
ms
pp16+tg1536
203
tokens/s
31.5
tokens/s
108
ms