TEST #3276 RESULTS
04/10/2026 - 7:12 PM
ACCELERATOR
MODEL
12.4
tokens/s
generation
654
ms
time to first token
2532
tokens/s
prompt
364
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 7600X 6-Core Processor (znver4)
RAM
30.4GB
OS
Linux
Kernel Release
6.12.63
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1-NixOS SMP PREEMPT_DYNAMIC Thu Dec 18 12:55:23 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3456
tokens/s
14.0
tokens/s
368
ms
pp4096+tg256
1781
tokens/s
4.2
tokens/s
2.53
sec
pp2048+tg256
2589
tokens/s
8.8
tokens/s
919
ms
pp2048+tg768
2641
tokens/s
7.9
tokens/s
901
ms
pp1024+tg1024
3399
tokens/s
11.7
tokens/s
374
ms
pp1280+tg3072
2996
tokens/s
6.7
tokens/s
536
ms
pp384+tg1152
3675
tokens/s
16.5
tokens/s
147
ms
pp64+tg1024
1678
tokens/s
23.2
tokens/s
61
ms
pp16+tg1536
572
tokens/s
18.9
tokens/s
48
ms