TEST #2770 RESULTS
02/21/2026 - 5:02 PM
ACCELERATOR
MODEL
52.4
tokens/s
generation
3.28
sec
time to first token
454
tokens/s
prompt
194
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5900X 12-Core Processor (znver3)
RAM
31.9GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
470
tokens/s
55.8
tokens/s
2.20
sec
pp4096+tg256
351
tokens/s
44.9
tokens/s
11.69
sec
pp2048+tg256
416
tokens/s
50.9
tokens/s
4.94
sec
pp2048+tg768
429
tokens/s
49.4
tokens/s
4.80
sec
pp1024+tg1024
486
tokens/s
53.0
tokens/s
2.13
sec
pp1280+tg3072
468
tokens/s
48.0
tokens/s
2.75
sec
pp384+tg1152
499
tokens/s
55.6
tokens/s
787
ms
pp64+tg1024
612
tokens/s
57.2
tokens/s
122
ms
pp16+tg1536
355
tokens/s
56.4
tokens/s
62
ms