Ollama model feed-back
From Notes_Wiki
Home > Local system based AI tools > Ollama > Ollama model feed-back
We can go to https://ollama.com/ and get information on large no. of models available include their parameter options 9B or 70B etc. and for each type of parameter option we can also see the size of model on the page.
Based on the available memory on the system and advantages of particular model we can download it. The name through which can download the model is also written before the size. For example at https://ollama.com/library/phi3 we can see that phi3 is available for 3.8b billion parameters for 2.2GB size and can be downloaded via:
ollama run phi3
Overall for following models I can share feed-back:
- deepseek-r1 (Multiple sizes)
- : Very good model with thinking / chain of thought so that we get very good results with explanation
- phi4 (14B - 9.1GB)
- : Very high accuracy among small models
- llama3.2 (3B - 2.0 GB)
- : Very small and efficient model that can be run with limited resources
- llama3 (8B - 4.7GB)
- : Decently sized to run on local laptop, be fast, memory efficient and still give reasonable output.
- llava (34b - 20GB)
- : For image recognition or computer vision related tasks
- llama3.2-vision (11b - 7.9GB)
- : For image recognition tasks with smaller size
- wizard-vicuna-uncensored (30b - 18GB)
- : For queries that would otherwise get censored on other models
Home > Local system based AI tools > Ollama > Ollama model feed-back