TEST #3433 RESULTS
05/03/2026 - 10:37 PM
ACCELERATOR
MODEL
21.9
tokens/s
generation
3.51
sec
time to first token
462
tokens/s
prompt
142
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.1 8B Instruct Abliterated_Via_Adapter - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 5700G with Radeon Graphics (znver3)
RAM
15GB
OS
Linux
Kernel Release
6.19.13-arch1-1
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Tue, 21 Apr 2026 23:38:22 +0000
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
495
tokens/s
28.7
tokens/s
2.10
sec
pp4096+tg256
292
tokens/s
3.3
tokens/s
14.30
sec
pp2048+tg256
423
tokens/s
19.9
tokens/s
4.89
sec
pp2048+tg768
426
tokens/s
18.3
tokens/s
4.85
sec
pp1024+tg1024
517
tokens/s
23.8
tokens/s
2.02
sec
pp1280+tg3072
513
tokens/s
11.9
tokens/s
2.53
sec
pp384+tg1152
600
tokens/s
28.5
tokens/s
669
ms
pp64+tg1024
569
tokens/s
32.2
tokens/s
139
ms
pp16+tg1536
322
tokens/s
30.3
tokens/s
76
ms