TEST #1589 RESULTS
10/05/2025 - 2:37 PM
ACCELERATOR
MODEL
60.4
tokens/s
generation
3.47
sec
time to first token
421
tokens/s
prompt
194
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 7700 8-Core Processor (znver4)
RAM
31.2GB
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
440
tokens/s
64.4
tokens/s
2.34
sec
pp4096+tg256
345
tokens/s
51.6
tokens/s
11.88
sec
pp2048+tg256
396
tokens/s
59.6
tokens/s
5.19
sec
pp2048+tg768
390
tokens/s
57.8
tokens/s
5.27
sec
pp1024+tg1024
420
tokens/s
61.3
tokens/s
2.45
sec
pp1280+tg3072
425
tokens/s
55.1
tokens/s
3.02
sec
pp384+tg1152
459
tokens/s
63.6
tokens/s
853
ms
pp64+tg1024
564
tokens/s
65.2
tokens/s
129
ms
pp16+tg1536
349
tokens/s
65.1
tokens/s
60
ms