Wilson Cheng's picture

Wilson Cheng

wilsoncheng

·

[email protected]

AI & ML interests

None yet

Recent Activity

reacted to danielhanchen's post with ❤️ about 2 months ago

Run OpenAI's new gpt-oss models locally with Unsloth GGUFs! 🔥🦥 20b GGUF: https://huggingface.co/unsloth/gpt-oss-20b-GGUF 120b GGUF: https://huggingface.co/unsloth/gpt-oss-120b-GGUF Model will run on 14GB RAM for 20b and 66GB for 120b.

reacted to danielhanchen's post with ❤️ about 2 months ago

Run DeepSeek-V3.1 locally on 170GB RAM with Dynamic 1-bit GGUFs!🐋 GGUFs: https://huggingface.co/unsloth/DeepSeek-V3.1-GGUF The 715GB model gets reduced to 170GB (-80% size) by smartly quantizing layers. The 1-bit GGUF passes all our code tests & we fixed the chat template for llama.cpp supported backends. Guide: https://docs.unsloth.ai/basics/deepseek-v3.1

published a Space 6 months ago

wilsoncheng/mistralai-Magistral-Small-2506

View all activity

Organizations

None yet

spaces 1

Mistralai Magistral Small 2506

Sign in and generate text with Magistral-Small-2506 model

models 2

wilsoncheng/Gemma-3-4B-Fin-QA-Reasoning

Any-to-Any • 4B • Updated Apr 27 • 5

wilsoncheng/gemma-product-description

datasets 0

None public yet