TEST #1472 RESULTS
09/03/2025 - 5:19 AM
ACCELERATOR
MODEL
49.8
tokens/s
generation
3.85
sec
time to first token
386
tokens/s
prompt
171
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 3900X 12-Core Processor (znver2)
RAM
62.7GB
OS
Linux
Kernel Release
6.8.0-49-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #49~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Nov 6 17:42:15 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
397
tokens/s
52.6
tokens/s
2.60
sec
pp4096+tg256
302
tokens/s
43.3
tokens/s
13.59
sec
pp2048+tg256
360
tokens/s
47.7
tokens/s
5.72
sec
pp2048+tg768
358
tokens/s
47.9
tokens/s
5.74
sec
pp1024+tg1024
398
tokens/s
50.5
tokens/s
2.59
sec
pp1280+tg3072
388
tokens/s
46.4
tokens/s
3.32
sec
pp384+tg1152
427
tokens/s
52.5
tokens/s
917
ms
pp64+tg1024
453
tokens/s
54.4
tokens/s
159
ms
pp16+tg1536
388
tokens/s
53.2
tokens/s
59
ms