TEST #901 RESULTS
05/18/2025 - 7:43 PM
ACCELERATOR
MODEL
36.6
tokens/s
generation
6.75
sec
time to first token
223
tokens/s
prompt
107
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 5600U with Radeon Graphics (znver3)
RAM
62.1GB
OS
Linux
Kernel Release
6.12.13-200.fc41.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sat Feb 8 20:05:26 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
231
tokens/s
39.4
tokens/s
4.46
sec
pp4096+tg256
176
tokens/s
30.9
tokens/s
23.33
sec
pp2048+tg256
204
tokens/s
36.1
tokens/s
10.06
sec
pp2048+tg768
200
tokens/s
33.9
tokens/s
10.25
sec
pp1024+tg1024
218
tokens/s
37.0
tokens/s
4.72
sec
pp1280+tg3072
214
tokens/s
33.8
tokens/s
6.00
sec
pp384+tg1152
251
tokens/s
38.7
tokens/s
1.55
sec
pp64+tg1024
275
tokens/s
40.6
tokens/s
256
ms
pp16+tg1536
233
tokens/s
39.6
tokens/s
91
ms