TEST #3906 RESULTS
07/14/2026 - 9:18 PM
ACCELERATOR
MODEL
30.7
tokens/s
generation
2.46
sec
time to first token
564
tokens/s
prompt
192
LocalScore
HOW YOU STACK UP
Explore All ResultsHf_Model - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 2600 Six-Core Processor
RAM
7.7GB
OS
Linux
Kernel Release
7.0.12-arch1-1
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Wed, 10 Jun 2026 08:58:02 +0000
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
637
tokens/s
37.9
tokens/s
1.63
sec
pp4096+tg256
477
tokens/s
12.7
tokens/s
8.66
sec
pp2048+tg256
572
tokens/s
22.1
tokens/s
3.62
sec
pp2048+tg768
568
tokens/s
20.1
tokens/s
3.65
sec
pp1024+tg1024
627
tokens/s
28.6
tokens/s
1.66
sec
pp1280+tg3072
610
tokens/s
17.7
tokens/s
2.13
sec
pp384+tg1152
683
tokens/s
39.5
tokens/s
578
ms
pp64+tg1024
647
tokens/s
52.8
tokens/s
110
ms
pp16+tg1536
252
tokens/s
44.6
tokens/s
73
ms