
Pluto 1
A 1.2B Instruct model for quick answers. 100+ tokens per second on GPUs, up to 50 on CPU. Non-reasoning. Almost as good as a 2B, far faster. 1.2B parameters.
80 downloads
Pluto 1 and Pluto 0.5 are archived. The last open-weight Plutos. Neptun3

A 1.2B Instruct model for quick answers. 100+ tokens per second on GPUs, up to 50 on CPU. Non-reasoning. Almost as good as a 2B, far faster. 1.2B parameters.
80 downloads
No reviews yet
Shared with everyone. No account.

The fastest 350M parameter model. It beats 500M models in math and general questions. 350M parameters.
No reviews yet
Shared with everyone. No account.
Poe
Open the Wolkyen profile on Poe.
A 350M open-weight model with a hybrid architecture, native tool use, and quantizations that run on your own hardware. 350M parameters.
218 downloads
ollama run hf.co/Wolkyen/Neptun3-One:Q4_K_MNo reviews yet
Shared with everyone. No account.
Magi Bot is still here if you need it. magi_bot.py