TEST #1587 RESULTS
10/05/2025 - 10:19 AM
ACCELERATOR
MODEL
41.4
tokens/s
generation
173
ms
time to first token
9013
tokens/s
prompt
1292
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 7800X3D 8-Core Processor (znver4)
RAM
15.5GB
OS
Linux
Kernel Release
6.6.87.2-microsoft-standard-WSL2
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Thu Jun 5 18:30:46 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
13671
tokens/s
59.4
tokens/s
89
ms
pp4096+tg256
8618
tokens/s
34.8
tokens/s
505
ms
pp2048+tg256
12565
tokens/s
43.2
tokens/s
188
ms
pp2048+tg768
8292
tokens/s
37.0
tokens/s
296
ms
pp1024+tg1024
14074
tokens/s
40.1
tokens/s
123
ms
pp1280+tg3072
7606
tokens/s
37.6
tokens/s
194
ms
pp384+tg1152
12812
tokens/s
41.9
tokens/s
47
ms
pp64+tg1024
2922
tokens/s
42.0
tokens/s
37
ms
pp16+tg1536
558
tokens/s
36.2
tokens/s
78
ms