Sublime
An inspiration engine for ideas

Tutorial: Train your own Reasoning LLM for free!
Make Llama 3.1 (8B) have chain-of-thought with DeepSeek's GRPO. Unsloth enables 90% less VRAM use.
Learn about:
• Reward Functions + dataset prep
• Training on free Colab GPUs
• Run +... See more
2-5x faster 50% less memory local LLM finetuning
- Manual autograd engine - hand derived backprop steps.
- 2x to 5x faster than QLoRA. 50% less memory usage.
- All kernels written in OpenAI's Triton language.
- 0% loss in accuracy - no approximation methods - all exact.
- No change of hardware necessary. Supports NVIDIA GPUs since 2018+. Minimum CUDA Compute
unslothai • GitHub - unslothai/unsloth: 5X faster 50% less memory LLM finetuning

👨🔧 Github: Native, Apple Silicon–only local LLM server. Similar to Ollama, but built on Apple's MLX
- OpenAI API compatible,
- Ollama‑compatible
- OpenAI‑style tools + tool_choice, with tool_calls parsing and streaming deltas
github. com/dinoki-ai/osaurus... See more
I made Computer Use work for MacOS directly and let it loose on my actual computer!!
Anthropic's "safe" Ubuntu docker demo was too painful. In this video (8x), it creates a Double Pendulum simulator from scratch and opens it up in Chrome.
Put it all on Github too. Feel the AGI.... See more
Deedyx.comIntroducing the Token Monster 👾
The most powerful chatbot on Earth. Period.
Automatically routes prompts to the best models + combines results:
→ Claude for creativity
→ o3 for reasoning
→ PPLX for research
+... See more
Matt Shumerx.com