Choosing the Right LLM for Cognee: Local Ollama Setup.

Choosing the Right LLM for Cognee: Local Ollama Setup - Comparing qwen3:14b, gpt-oss20b, devstral 2 small, and others https://www.glukhov.org/post/2025/12/choosing-right-llm-for-cognee-on-ollama/ #SelfHosting #LLM #AI #Ollama #RAG #Python

Comments

Post a Comment

Popular posts from this blog

Argumentum Ad Baculum - Definition and Examples

In the pursuit of truth and sound reasoning, fallacies present themselves as deceptive snares that can ensnare even the most critical thinker. Among these is the ad baculum fallacy, or appeal to force, a fallacious argumentative tactic that employs coercion or threats to support a conclusion. This article provides an in-depth exploration of the ad baculum fallacy, unveiling its subtleties, historical roots, and the impact it has on discourse and decision-making. Definition and Origins The phrase argumentum ad baculum is derived from Latin, meaning “argument to the stick,” or “appeal to the force” symbolizing the use of force or threat. This fallacy occurs when an argument is supported by a threat of negative consequences rather than by legitimate evidence or reasoning. It is a persuasive strategy that relies on fear to compel acceptance of a claim.
Read more

Move Ollama Models to different location

After installing ollama better to reconfigure ollama to store them in new place right away. So after we pull a new model, it doesn’t get downloaded to the old location. Ollama is a text-based frontend to LLM AI Models and an API that can host those too. Install Ollama Goto https://ollama.com/download To install Ollama on linux: curl -fsSL https://ollama.com/install.sh | sh Ollama on Windows is on page: https://ollama.com/download/windows Ollama for Mac is there too: https://ollama.com/download/macOllamaSetup.exe Download, List and Remove Ollama models To download some Ollama models: Go to Ollama Library (https://ollama.com/library) and find the model you need, there you can also find model tags and sizes. Then run: ollama pull gemma2:latest # Or get slightly smarter one still nicely fitting into 16GB VRAM: ollama pull gemma2:27b-instruct-q3_K_S # Or: ollama pull llama3.1:latest ollama pull llama3.1:8b-instruct-q8_0 ollama pull mistral-nemo:12b-instruct-2407-q6_K ollama ...
Read more