Story Details
| Last Updated | |
| Total Articles | 1 |
Main Topics
More articles on this subject
Previous
Next
Similar to This
Previous
github.com Oct 18
GitHub - achyudh/llama.cpp: LLM inference in C/C++: LLM inference in C/C++. Contribute to achyudh/llama.cpp development by creating an account on GitHub.
github.com/achyudh/llama.cpp
I'm not paying $20 for ChatGPT or Claude because a free local LLM does everything I need
xda-developers.com/im-not-paying-20-for-chatgpt-claude-or-gemini-because-a-free-local-llm-does-everything-i-need/
Ollama is the easiest way to start with local AI, and it's also the first thing I'd replace
xda-developers.com/ollama-easiest-way-start-with-local-ai-its-also-first-thing-id-replace/
github.com Oct 16
model : MTP support for Mellum2.1 by Xarbirus · Pull Request #30612 · ggml-org/llama.cpp
github.com/ggml-org/llama.cpp/pull/30612
I moved my local models from Ollama to llama.cpp, and the reason I stayed has nothing to do with speed
xda-developers.com/i-moved-from-ollama-to-llamacpp-and-discovered-its-better-than-most-tools/
I ran GLM 5.3, a 744-billion-parameter model, on my home lab, and the frontier suddenly feels a lot closer
xda-developers.com/you-can-run-a-744b-model-on-your-own-hardware/
Ollama is the easiest way to start local LLMs, but these 6 alternatives are also worth trying
xda-developers.com/ollama-alternatives-worth-trying/
Llama.cpp, Speaches, and Open WebUI turned my Raspberry Pi into a voice assistant that actually works
xda-developers.com/i-built-a-voice-assistant-with-my-raspberry-pi/
I finally ditched Ollama after using llama.cpp's WebUI, and I'm not going back anytime soon
xda-developers.com/i-ditched-ollama-after-using-llama-cpp-webui-and-im-not-going-back/
I ditched LM Studio for llama.cpp, and my local LLM doesn't feel like a downgrade anymore
xda-developers.com/ditched-lm-studio-for-llama-cpp-and-local-llm-doesnt-feel-like-downgrade-anymore/
I ditched Copilot on VS Code for this free extension, and it's miles ahead: It's completely self-hosted, too!
xda-developers.com/i-ditched-copilot-for-this-free-vs-code-extension-and-its-miles-ahead/
github.com Apr 30
GitHub - Kaden-Schutt/hipfire: RDNA-native LLM inference engine in Rust.: RDNA-native LLM inference engine in Rust. . Contribute to Kaden-Schutt/hipfire ...
github.com/Kaden-Schutt/hipfire
github.com Apr 09
ggml: backend-agnostic tensor parallelism (experimental) by JohannesGaessler · Pull Request #19378 · ggml-org/llama.cpp
github.com/ggml-org/llama.cpp/pull/19378
Ollama is still the easiest way to start local LLMs, but it's the worst way to keep running them
xda-developers.com/ollama-easiest-way-start-local-llms-worst-keep-running/
Next