TEST #1018 RESULTS
06/07/2025 - 10:20 PM
ACCELERATOR
MODEL
32.4
tokens/s
generation
4.93
sec
time to first token
302
tokens/s
prompt
126
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
5.4.0-216-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #236-Ubuntu SMP Fri Apr 11 19:53:21 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
302
tokens/s
34.0
tokens/s
3.42
sec
pp4096+tg256
234
tokens/s
27.7
tokens/s
17.53
sec
pp2048+tg256
281
tokens/s
31.9
tokens/s
7.32
sec
pp2048+tg768
283
tokens/s
31.3
tokens/s
7.27
sec
pp1024+tg1024
317
tokens/s
32.9
tokens/s
3.26
sec
pp1280+tg3072
310
tokens/s
30.2
tokens/s
4.16
sec
pp384+tg1152
348
tokens/s
34.0
tokens/s
1.13
sec
pp64+tg1024
355
tokens/s
34.9
tokens/s
208
ms
pp16+tg1536
287
tokens/s
34.4
tokens/s
84
ms