TEST #3681 RESULTS
06/03/2026 - 3:35 PM
ACCELERATOR
MODEL
56.0
tokens/s
generation
2.81
sec
time to first token
514
tokens/s
prompt
217
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 7940HS w/ Radeon 780M Graphics (znver4)
RAM
60.6GB
OS
Linux
Kernel Release
7.0.10-201.fc44.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Wed May 27 13:57:41 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
551
tokens/s
60.1
tokens/s
1.87
sec
pp4096+tg256
414
tokens/s
46.2
tokens/s
9.92
sec
pp2048+tg256
494
tokens/s
54.5
tokens/s
4.16
sec
pp2048+tg768
492
tokens/s
53.1
tokens/s
4.18
sec
pp1024+tg1024
544
tokens/s
57.2
tokens/s
1.90
sec
pp1280+tg3072
538
tokens/s
51.1
tokens/s
2.39
sec
pp384+tg1152
599
tokens/s
59.4
tokens/s
658
ms
pp64+tg1024
506
tokens/s
61.9
tokens/s
143
ms
pp16+tg1536
485
tokens/s
60.6
tokens/s
48
ms