Hugging Face's logo

Collections

Discover the best community collections!

Collections trending this week
Qwen 3.6 - Reg/Uncensored 9b, 12b, 21b, 27b, 40B
Fine tuned Qwen 3.6 models, including source and GGUF from 9B and up. 9B,12B, 21B and 40B are custom built by me. Tuning via Unsloth on local hardware
Cactus Hybrid
A small, on-device model is fast and private, but sometimes wrong. We post-train models to know when they are wrong, run on any framework.
Ornith-1.0
Ornith-1.0 is  a family of open-source LLMs specialized for agentic coding.
Gemma 4
Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B.
Unsloth Dynamic 2.0 Quants
New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance.
Qwen 3.6 - Reg/Uncensored 9b, 12b, 21b, 27b, 40B
Fine tuned Qwen 3.6 models, including source and GGUF from 9B and up. 9B,12B, 21B and 40B are custom built by me. Tuning via Unsloth on local hardware
Ornith-1.0
Ornith-1.0 is  a family of open-source LLMs specialized for agentic coding.
Gemma 4
Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B.
Unsloth Dynamic 2.0 Quants
New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance.
Cactus Hybrid
A small, on-device model is fast and private, but sometimes wrong. We post-train models to know when they are wrong, run on any framework.