228
Llama 3.2 Reasoning WebGPU
ðŸ§
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 • 79 • 42
ngxson/MiniThinky-v2-1B-Llama-3.2-Q8_0-GGUF
1B • Updated • 11 • 8Note --- Old checkpoints:
-
ngxson/MiniThinky-1B-Llama-3.2
Text Generation • 1B • Updated • 7 • 4 -
ngxson/MiniThinky-1B-Llama-3.2-Q8_0-GGUF
1B • Updated • 2
ngxson/MiniThinky-1.7B-SmolLM2
Text Generation • 2B • UpdatedNote --- Dataset:
-
ngxson/MiniThinky-dataset
Viewer • Updated • 88.2k • 41 • 21