Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-experimental-0427

Text Generation • Updated 2 days ago • 36 • 1

Note MoE reasoning model with 3.91B params in total, and 2 experts active.

Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-experimental-0427-Q8_0-GGUF

Text Generation • Updated 6 days ago • 25

Note GGUF of superthoughts lite v2

Pinkstack/Superthoughts-lite-v1

Text Generation • Updated Mar 19 • 271 • 2

Note Non-experimental version of lite. 1.7B parameters, GRPO & SFT trained, not very conversational though.

Pinkstack/Superthoughts-lite-v1-GGUF

Updated Feb 22 • 125 • 1

Note Non-experimental version of lite. 1.7B parameters, GRPO & SFT trained. GGUF version.