TEST #2963 RESULTS
03/03/2026 - 12:51 PM
ACCELERATOR
MODEL
133
tokens/s
generation
95
ms
time to first token
13977
tokens/s
prompt
2693
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 7800X3D 8-Core Processor (znver4)
RAM
61.9GB
OS
Linux
Kernel Release
6.18.7-76061807-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #202601231045~1769703228~24.04~cb87b5b SMP PREEMPT_DYNAMIC Thu J
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
18709
tokens/s
152
tokens/s
61
ms
pp4096+tg256
13002
tokens/s
104
tokens/s
325
ms
pp2048+tg256
16464
tokens/s
134
tokens/s
132
ms
pp2048+tg768
16598
tokens/s
115
tokens/s
131
ms
pp1024+tg1024
18813
tokens/s
138
tokens/s
62
ms
pp1280+tg3072
17583
tokens/s
118
tokens/s
80
ms
pp384+tg1152
18921
tokens/s
146
tokens/s
27
ms
pp64+tg1024
4033
tokens/s
142
tokens/s
24
ms
pp16+tg1536
1667
tokens/s
149
tokens/s
16
ms