Llama 3.2 Reasoning WebGPU
🧠
229
Small and powerful reasoning LLM that runs in your browser
MiniThinky: extra small reasoning models
My first trial to make reasoning models
-
-
ngxson/MiniThinky-v2-1B-Llama-3.2
Text Generation • 1B • Updated • 87 • 43
ngxson/MiniThinky-v2-1B-Llama-3.2-Q8_0-GGUF
1B • Updated • 16 • 8Note --- Old checkpoints:
-
ngxson/MiniThinky-1B-Llama-3.2
Text Generation • 1B • Updated • 8 • 4 -
ngxson/MiniThinky-1B-Llama-3.2-Q8_0-GGUF
1B • Updated
ngxson/MiniThinky-1.7B-SmolLM2
Text Generation • 2B • Updated • 1Note --- Dataset:
-
ngxson/MiniThinky-dataset
Viewer • Updated • 88.2k • 28 • 21