TEST #1609 RESULTS
10/07/2025 - 9:19 PM
ACCELERATOR
MODEL
14.4
tokens/s
generation
4.99
sec
time to first token
293
tokens/s
prompt
95
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 3B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-10400 CPU @ 2.90GHz (skylake)
RAM
31.3GB
OS
Linux
Kernel Release
6.8.0-84-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #84-Ubuntu SMP PREEMPT_DYNAMIC Fri Sep 5 22:36:38 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
314
tokens/s
17.8
tokens/s
3.31
sec
pp4096+tg256
234
tokens/s
5.3
tokens/s
17.66
sec
pp2048+tg256
280
tokens/s
9.7
tokens/s
7.41
sec
pp2048+tg768
280
tokens/s
8.8
tokens/s
7.41
sec
pp1024+tg1024
310
tokens/s
12.9
tokens/s
3.37
sec
pp1280+tg3072
304
tokens/s
7.6
tokens/s
4.28
sec
pp384+tg1152
336
tokens/s
18.8
tokens/s
1.18
sec
pp64+tg1024
341
tokens/s
26.9
tokens/s
204
ms
pp16+tg1536
237
tokens/s
21.7
tokens/s
81
ms