TEST #713 RESULTS
04/14/2025 - 4:36 AM
ACCELERATOR
MODEL
339
tokens/s
generation
91
ms
time to first token
14601
tokens/s
prompt
3789
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 7302P 16-Core Processor (znver2)
RAM
62.7GB
OS
Linux
Kernel Release
6.11.0-21-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #21~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Feb 24 16:52:15 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
18969
tokens/s
354
tokens/s
57
ms
pp4096+tg256
12735
tokens/s
291
tokens/s
325
ms
pp2048+tg256
16437
tokens/s
334
tokens/s
128
ms
pp2048+tg768
16300
tokens/s
328
tokens/s
129
ms
pp1024+tg1024
18811
tokens/s
345
tokens/s
57
ms
pp1280+tg3072
17614
tokens/s
316
tokens/s
76
ms
pp384+tg1152
19852
tokens/s
355
tokens/s
22
ms
pp64+tg1024
9568
tokens/s
368
tokens/s
9
ms
pp16+tg1536
1124
tokens/s
361
tokens/s
17
ms