TEST #136 RESULTS
03/28/2025 - 10:17 PM
ACCELERATOR
MODEL
342
tokens/s
generation
83
ms
time to first token
17080
tokens/s
prompt
4130
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 7352 24-Core Processor (znver2)
RAM
125.7GB
OS
Linux
Kernel Release
5.15.0-118-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #128-Ubuntu SMP Fri Jul 5 09:28:59 UTC 2024
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
22145
tokens/s
349
tokens/s
49
ms
pp4096+tg256
13146
tokens/s
302
tokens/s
315
ms
pp2048+tg256
18453
tokens/s
337
tokens/s
114
ms
pp2048+tg768
18392
tokens/s
333
tokens/s
114
ms
pp1024+tg1024
22868
tokens/s
351
tokens/s
48
ms
pp1280+tg3072
21932
tokens/s
325
tokens/s
61
ms
pp384+tg1152
25656
tokens/s
358
tokens/s
18
ms
pp64+tg1024
10127
tokens/s
363
tokens/s
9
ms
pp16+tg1536
1005
tokens/s
361
tokens/s
19
ms