TEST #119 RESULTS
03/28/2025 - 9:59 PM
ACCELERATOR
MODEL
214
tokens/s
generation
222
ms
time to first token
6358
tokens/s
prompt
1830
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 5600X 6-Core Processor (znver3)
RAM
31.3GB
OS
Linux
Kernel Release
5.15.0-131-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #141~20.04.1-Ubuntu SMP Thu Jan 16 18:38:51 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
7813
tokens/s
228
tokens/s
136
ms
pp4096+tg256
5034
tokens/s
173
tokens/s
820
ms
pp2048+tg256
6604
tokens/s
207
tokens/s
315
ms
pp2048+tg768
6606
tokens/s
200
tokens/s
315
ms
pp1024+tg1024
7827
tokens/s
219
tokens/s
135
ms
pp1280+tg3072
7356
tokens/s
194
tokens/s
178
ms
pp384+tg1152
8965
tokens/s
231
tokens/s
47
ms
pp64+tg1024
6573
tokens/s
242
tokens/s
14
ms
pp16+tg1536
446
tokens/s
235
tokens/s
40
ms