TEST #926 RESULTS
05/22/2025 - 6:23 AM
ACCELERATOR
MODEL
13.9
tokens/s
generation
615
ms
time to first token
2435
tokens/s
prompt
380
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
3292
tokens/s
14.8
tokens/s
379
ms
pp4096+tg256
2063
tokens/s
4.4
tokens/s
2.22
sec
pp2048+tg256
2709
tokens/s
10.0
tokens/s
873
ms
pp2048+tg768
2697
tokens/s
9.2
tokens/s
879
ms
pp1024+tg1024
3248
tokens/s
13.4
tokens/s
383
ms
pp1280+tg3072
2915
tokens/s
7.8
tokens/s
518
ms
pp384+tg1152
3398
tokens/s
18.5
tokens/s
151
ms
pp64+tg1024
1119
tokens/s
25.8
tokens/s
80
ms
pp16+tg1536
476
tokens/s
21.4
tokens/s
53
ms