TEST #927 RESULTS
05/22/2025 - 6:25 AM
ACCELERATOR
MODEL
16.6
tokens/s
generation
418
ms
time to first token
3681
tokens/s
prompt
527
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama-3.2-1B-Instruct - Q4_0
SYSTEM
CPU
AMD Ryzen 7 7800X3D 8-Core Processor (znver4)
RAM
61.9GB
OS
Linux
Kernel Release
6.11.0-25-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #25~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Apr 15 17:20:50 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
5248
tokens/s
17.8
tokens/s
251
ms
pp4096+tg256
3181
tokens/s
4.7
tokens/s
1.49
sec
pp2048+tg256
4163
tokens/s
11.9
tokens/s
590
ms
pp2048+tg768
4144
tokens/s
10.8
tokens/s
593
ms
pp1024+tg1024
4975
tokens/s
15.5
tokens/s
262
ms
pp1280+tg3072
4295
tokens/s
8.9
tokens/s
365
ms
pp384+tg1152
4989
tokens/s
22.4
tokens/s
108
ms
pp64+tg1024
1464
tokens/s
31.7
tokens/s
62
ms
pp16+tg1536
673
tokens/s
25.7
tokens/s
39
ms