The tutorials cover a range of open model families including Qwen, Kimi, and Llama, detailing their strengths, weaknesses, and performance benchmarks. Each model tutorial includes descriptions and use cases, alongside instructions for running the models on various platforms like llama.cpp and Ollama. Detailed fine-tuning instructions and practical tips are provided for Unsloth users to optimize model implementations, addressing potential issues experienced during execution. Specific examples include benchmarks for models and suggestions for installing and running these models effectively.
Qwen3-Coder-480B-A35B delivers SOTA advancements in agentic coding and code tasks, matching or outperforming Claude Sonnet-4, GPT-4.1, and Kimi K2. The 480B model achieves a 61.8% on Aider Polygot and supports a 256K token context, extendable to 1M tokens.
Install ollama if you haven't already! apt-get update apt-get install pciutils -y curl -fsSL https://ollama.com/install.sh | sh Run the model! Note you can call ollama serve in another terminal if it fails!
Gemma 3n, like Gemma 3, had issues running on Flotat16 GPUs such as Tesla T4s in Colab. You will encounter NaNs and infinities if you do not patch Gemma.
Collection
[
|
...
]