Mostafa Maher

Devostafa

AI & ML interests

None yet

Recent Activity

liked a model 1 day ago

mradermacher/Nanbeige4.1-3B-absolute-heresy-i1-GGUF

liked a model 2 days ago

tarekys5/qwen2.5-egyptian-legalv1

reacted to danielhanchen's post with 🤗 6 days ago

We collaborated with Hugging Face to enable you to train MoE models 12× faster with 35% less VRAM via our new Triton kernels (no accuracy loss). 🤗 Train gpt-oss locally on 12.8GB VRAM with our free notebooks: https://unsloth.ai/docs/new/faster-moe

View all activity

Organizations

None yet

liked a model 1 day ago

mradermacher/Nanbeige4.1-3B-absolute-heresy-i1-GGUF

4B • Updated 1 day ago • 2.17k • 2

liked a model 2 days ago

tarekys5/qwen2.5-egyptian-legalv1

Question Answering • 3B • Updated 4 days ago • 59 • 1

reacted to danielhanchen's post with 🤗🔥 6 days ago

Post

5074

We collaborated with Hugging Face to enable you to train MoE models 12× faster with 35% less VRAM via our new Triton kernels (no accuracy loss). 🤗

Train gpt-oss locally on 12.8GB VRAM with our free notebooks: https://unsloth.ai/docs/new/faster-moe

1 reply

liked a model 7 days ago

mradermacher/Think2SQL-4B-i1-GGUF

4B • Updated 7 days ago • 1.87k • 1

reacted to danielhanchen's post with ❤️ 12 days ago

Post

3639

We created a tool-calling guide for local LLMs!

Learn how to use any open model like Qwen3-Coder-Next and GLM-4.7-Flash for function calling.

Guide: https://unsloth.ai/docs/basics/tool-calling-guide-for-local-llms

We provide hands-on examples for: story writing, Python execution, terminal tool calls, maths and more.