TEST #435 RESULTS
04/06/2025 - 9:49 PM
ACCELERATOR
MODEL
254
tokens/s
generation
166
ms
time to first token
8609
tokens/s
prompt
2361
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 3700X 8-Core Processor (znver2)
RAM
31.3GB
OS
Linux
Kernel Release
6.8.0-55-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #57-Ubuntu SMP PREEMPT_DYNAMIC Wed Feb 12 23:42:21 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
10396
tokens/s
259
tokens/s
102
ms
pp4096+tg256
6598
tokens/s
212
tokens/s
626
ms
pp2048+tg256
8788
tokens/s
241
tokens/s
237
ms
pp2048+tg768
8835
tokens/s
237
tokens/s
236
ms
pp1024+tg1024
10609
tokens/s
256
tokens/s
101
ms
pp1280+tg3072
10536
tokens/s
245
tokens/s
125
ms
pp384+tg1152
12607
tokens/s
276
tokens/s
34
ms
pp64+tg1024
8300
tokens/s
283
tokens/s
11
ms
pp16+tg1536
814
tokens/s
279
tokens/s
23
ms