TEST #1349 RESULTS
08/09/2025 - 10:22 PM
ACCELERATOR
MODEL
95.6
tokens/s
generation
409
ms
time to first token
3575
tokens/s
prompt
942
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
31.3GB
OS
Linux
Kernel Release
6.8.0-71-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #71-Ubuntu SMP PREEMPT_DYNAMIC Tue Jul 22 16:52:38 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4672
tokens/s
122
tokens/s
227
ms
pp4096+tg256
2621
tokens/s
18.1
tokens/s
1.62
sec
pp2048+tg256
3597
tokens/s
85.6
tokens/s
581
ms
pp2048+tg768
3598
tokens/s
80.4
tokens/s
581
ms
pp1024+tg1024
4498
tokens/s
99.2
tokens/s
236
ms
pp1280+tg3072
4269
tokens/s
56.9
tokens/s
309
ms
pp384+tg1152
5005
tokens/s
120
tokens/s
83
ms
pp64+tg1024
2262
tokens/s
145
tokens/s
34
ms
pp16+tg1536
1652
tokens/s
134
tokens/s
15
ms