TEST #913 RESULTS
05/19/2025 - 5:05 AM
ACCELERATOR
MODEL
12.8
tokens/s
generation
644
ms
time to first token
2552
tokens/s
prompt
371
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 7900X 12-Core Processor (znver4)
RAM
62GB
OS
Linux
Kernel Release
6.5.0-41-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #41~22.04.2-Ubuntu SMP PREEMPT_DYNAMIC Mon Jun 3 11:32:55 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3460
tokens/s
14.4
tokens/s
366
ms
pp4096+tg256
1820
tokens/s
3.9
tokens/s
2.50
sec
pp2048+tg256
2669
tokens/s
9.1
tokens/s
891
ms
pp2048+tg768
2642
tokens/s
8.1
tokens/s
899
ms
pp1024+tg1024
3408
tokens/s
11.9
tokens/s
372
ms
pp1280+tg3072
2980
tokens/s
6.7
tokens/s
516
ms
pp384+tg1152
3924
tokens/s
17.4
tokens/s
136
ms
pp64+tg1024
1546
tokens/s
24.4
tokens/s
65
ms
pp16+tg1536
515
tokens/s
19.9
tokens/s
52
ms