TEST #1875 RESULTS
11/26/2025 - 7:41 PM
ACCELERATOR
MODEL
432
tokens/s
generation
52
ms
time to first token
27767
tokens/s
prompt
6127
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
125.7GB
OS
Linux
Kernel Release
6.17.7-200.fc42.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sun Nov 2 17:43:34 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
36124
tokens/s
444
tokens/s
31
ms
pp4096+tg256
20470
tokens/s
379
tokens/s
203
ms
pp2048+tg256
29386
tokens/s
415
tokens/s
72
ms
pp2048+tg768
29497
tokens/s
415
tokens/s
72
ms
pp1024+tg1024
36900
tokens/s
433
tokens/s
30
ms
pp1280+tg3072
35546
tokens/s
406
tokens/s
38
ms
pp384+tg1152
42027
tokens/s
454
tokens/s
11
ms
pp64+tg1024
15056
tokens/s
474
tokens/s
6
ms
pp16+tg1536
4901
tokens/s
463
tokens/s
5
ms