TEST #50 RESULTS
03/28/2025 - 8:42 PM
ACCELERATOR
MODEL
315
tokens/s
generation
102
ms
time to first token
13191
tokens/s
prompt
3438
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 7543 32-Core Processor (znver3)
RAM
503.7GB
OS
Linux
Kernel Release
5.4.0-155-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #172-Ubuntu SMP Fri Jul 7 16:10:02 UTC 2023
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
17177
tokens/s
323
tokens/s
63
ms
pp4096+tg256
11109
tokens/s
271
tokens/s
372
ms
pp2048+tg256
14632
tokens/s
309
tokens/s
143
ms
pp2048+tg768
14228
tokens/s
304
tokens/s
147
ms
pp1024+tg1024
17297
tokens/s
321
tokens/s
62
ms
pp1280+tg3072
15521
tokens/s
297
tokens/s
86
ms
pp384+tg1152
18836
tokens/s
330
tokens/s
23
ms
pp64+tg1024
8470
tokens/s
344
tokens/s
10
ms
pp16+tg1536
1452
tokens/s
338
tokens/s
14
ms