TEST #1753 RESULTS
11/08/2025 - 1:49 AM
ACCELERATOR
MODEL
131
tokens/s
generation
313
ms
time to first token
4184
tokens/s
prompt
1207
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 5800X 8-Core Processor (znver3)
RAM
31.2GB
OS
Linux
Kernel Release
6.14.0-34-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #34~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Sep 23 15:35:20 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
5570
tokens/s
162
tokens/s
190
ms
pp4096+tg256
3683
tokens/s
39.3
tokens/s
1.14
sec
pp2048+tg256
4645
tokens/s
113
tokens/s
450
ms
pp2048+tg768
4702
tokens/s
106
tokens/s
444
ms
pp1024+tg1024
5290
tokens/s
136
tokens/s
200
ms
pp1280+tg3072
5019
tokens/s
87.4
tokens/s
262
ms
pp384+tg1152
5208
tokens/s
167
tokens/s
79
ms
pp64+tg1024
1773
tokens/s
194
tokens/s
40
ms
pp16+tg1536
1764
tokens/s
178
tokens/s
13
ms