TEST #1334 RESULTS
08/07/2025 - 8:29 AM
ACCELERATOR
MODEL
34.0
tokens/s
generation
1.80
sec
time to first token
743
tokens/s
prompt
241
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 3B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-6600K CPU @ 3.50GHz (skylake)
RAM
15.1GB
OS
Linux
Kernel Release
6.14.0-27-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #27-Ubuntu SMP PREEMPT_DYNAMIC Tue Jul 22 17:01:58 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
843
tokens/s
38.6
tokens/s
1.24
sec
pp4096+tg256
675
tokens/s
22.8
tokens/s
6.11
sec
pp2048+tg256
775
tokens/s
31.3
tokens/s
2.67
sec
pp2048+tg768
772
tokens/s
29.7
tokens/s
2.69
sec
pp1024+tg1024
831
tokens/s
34.6
tokens/s
1.26
sec
pp1280+tg3072
806
tokens/s
27.7
tokens/s
1.62
sec
pp384+tg1152
873
tokens/s
38.8
tokens/s
463
ms
pp64+tg1024
736
tokens/s
42.1
tokens/s
108
ms
pp16+tg1536
374
tokens/s
40.2
tokens/s
63
ms