TEST #4095 RESULTS
08/28/2026 - 9:15 AM
ACCELERATOR
MODEL
44.9
tokens/s
generation
3.06
sec
time to first token
506
tokens/s
prompt
195
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5950X 16-Core Processor (znver3)
RAM
62.7GB
OS
Linux
Kernel Release
7.2.0-1-cachyos
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Thu, 20 Aug 2026 16:18:38 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
528
tokens/s
47.6
tokens/s
1.96
sec
pp4096+tg256
357
tokens/s
38.3
tokens/s
11.50
sec
pp2048+tg256
468
tokens/s
41.9
tokens/s
4.40
sec
pp2048+tg768
445
tokens/s
42.6
tokens/s
4.63
sec
pp1024+tg1024
578
tokens/s
45.3
tokens/s
1.79
sec
pp1280+tg3072
521
tokens/s
42.1
tokens/s
2.48
sec
pp384+tg1152
630
tokens/s
47.5
tokens/s
629
ms
pp64+tg1024
594
tokens/s
49.7
tokens/s
130
ms
pp16+tg1536
430
tokens/s
49.1
tokens/s
56
ms