TEST #878 RESULTS
05/15/2025 - 5:15 AM
ACCELERATOR
MODEL
321
tokens/s
generation
99
ms
time to first token
13357
tokens/s
prompt
3510
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
125.6GB
OS
Linux
Kernel Release
6.11.0-25-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #25~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Apr 15 17:20:50 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
16799
tokens/s
328
tokens/s
64
ms
pp4096+tg256
11661
tokens/s
277
tokens/s
355
ms
pp2048+tg256
15371
tokens/s
318
tokens/s
136
ms
pp2048+tg768
15397
tokens/s
311
tokens/s
136
ms
pp1024+tg1024
17969
tokens/s
314
tokens/s
60
ms
pp1280+tg3072
16042
tokens/s
303
tokens/s
83
ms
pp384+tg1152
17936
tokens/s
341
tokens/s
24
ms
pp64+tg1024
8189
tokens/s
352
tokens/s
11
ms
pp16+tg1536
844
tokens/s
344
tokens/s
22
ms