TEST #701 RESULTS
04/12/2025 - 3:34 PM
ACCELERATOR
MODEL
10.0
tokens/s
generation
657
ms
time to first token
2563
tokens/s
prompt
339
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 8500G w/ Radeon 740M Graphics (znver4)
RAM
31.1GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3538
tokens/s
11.3
tokens/s
374
ms
pp4096+tg256
1799
tokens/s
3.3
tokens/s
2.57
sec
pp2048+tg256
2815
tokens/s
7.3
tokens/s
882
ms
pp2048+tg768
2820
tokens/s
6.2
tokens/s
881
ms
pp1024+tg1024
3344
tokens/s
9.6
tokens/s
405
ms
pp1280+tg3072
3172
tokens/s
5.4
tokens/s
508
ms
pp384+tg1152
3615
tokens/s
13.3
tokens/s
158
ms
pp64+tg1024
1414
tokens/s
18.1
tokens/s
75
ms
pp16+tg1536
551
tokens/s
15.3
tokens/s
52
ms