TEST #3677 RESULTS
06/03/2026 - 2:29 PM
ACCELERATOR
MODEL
56.1
tokens/s
generation
2.72
sec
time to first token
528
tokens/s
prompt
222
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
575
tokens/s
60.4
tokens/s
1.80
sec
pp4096+tg256
429
tokens/s
46.2
tokens/s
9.57
sec
pp2048+tg256
512
tokens/s
54.4
tokens/s
4.01
sec
pp2048+tg768
511
tokens/s
53.3
tokens/s
4.03
sec
pp1024+tg1024
561
tokens/s
56.9
tokens/s
1.84
sec
pp1280+tg3072
555
tokens/s
51.2
tokens/s
2.32
sec
pp384+tg1152
566
tokens/s
59.9
tokens/s
695
ms
pp64+tg1024
629
tokens/s
62.1
tokens/s
118
ms
pp16+tg1536
410
tokens/s
61.0
tokens/s
54
ms