TEST #3096 RESULTS
03/15/2026 - 8:13 PM
ACCELERATOR
MODEL
129
tokens/s
generation
119
ms
time to first token
10847
tokens/s
prompt
2272
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
13089
tokens/s
148
tokens/s
85
ms
pp4096+tg256
11055
tokens/s
98.7
tokens/s
381
ms
pp2048+tg256
13052
tokens/s
126
tokens/s
165
ms
pp2048+tg768
13100
tokens/s
114
tokens/s
164
ms
pp1024+tg1024
13124
tokens/s
134
tokens/s
85
ms
pp1280+tg3072
12791
tokens/s
111
tokens/s
107
ms
pp384+tg1152
15084
tokens/s
141
tokens/s
44
ms
pp64+tg1024
4687
tokens/s
143
tokens/s
24
ms
pp16+tg1536
1642
tokens/s
142
tokens/s
16
ms