TEST #3439 RESULTS
05/04/2026 - 6:12 PM
ACCELERATOR
MODEL
198
tokens/s
generation
118
ms
time to first token
11534
tokens/s
prompt
2687
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
31.9GB
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
14732
tokens/s
143
tokens/s
82
ms
pp4096+tg256
9860
tokens/s
194
tokens/s
421
ms
pp2048+tg256
12878
tokens/s
187
tokens/s
165
ms
pp2048+tg768
12837
tokens/s
205
tokens/s
165
ms
pp1024+tg1024
15342
tokens/s
213
tokens/s
72
ms
pp1280+tg3072
14421
tokens/s
206
tokens/s
94
ms
pp384+tg1152
16089
tokens/s
210
tokens/s
29
ms
pp64+tg1024
6320
tokens/s
212
tokens/s
15
ms
pp16+tg1536
1325
tokens/s
211
tokens/s
17
ms