whatcani.run
Home
Models
Device
Runs
Docs
GitHub
whatcani.run
Device Overview
Models tested
7
Tokens
921,600
Runs
18
Contributors
11
Model Speeds
Results include trials with
4,096
input tokens and
1,024
output tokens only.
Decode vs. Size
GGUF
MLX
Log
Prefill vs. Size
GGUF
MLX
Log
M3 Pro
·
36 GB
M3 Pro
·
36 GB
whatcani.run
Home
Models
Device
Runs
Docs
GitHub
Login
whatcani.run