TEST #880 RESULTS
05/15/2025 - 10:38 AM
ACCELERATOR
MODEL
16.4
tokens/s
generation
424
ms
time to first token
3644
tokens/s
prompt
520
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 7900X 12-Core Processor (znver4)
RAM
124.9GB
OS
Linux
Kernel Release
6.12.25
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Tue Apr 29 21:10:32 AEST 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
5200
tokens/s
17.5
tokens/s
254
ms
pp4096+tg256
3088
tokens/s
4.7
tokens/s
1.54
sec
pp2048+tg256
4143
tokens/s
11.7
tokens/s
594
ms
pp2048+tg768
4135
tokens/s
10.6
tokens/s
595
ms
pp1024+tg1024
5090
tokens/s
15.5
tokens/s
260
ms
pp1280+tg3072
4373
tokens/s
8.8
tokens/s
361
ms
pp384+tg1152
4831
tokens/s
22.1
tokens/s
110
ms
pp64+tg1024
1357
tokens/s
31.0
tokens/s
65
ms
pp16+tg1536
580
tokens/s
25.4
tokens/s
43
ms