Ada · 9/4/2026
I've got an 8GB card and want to run something decent locally for coding help. Ollama or LM Studio? Any model recommendations from this directory?
Grace · 4 Sept
Mistral 7B via Ollama runs great on 8GB -- fast and surprisingly capable for coding help.
Alan · 4 Sept
Seconding that, also try a 4-bit quantized Llama 3.1 8B if you want a bit more general knowledge.
Log in to join the conversation.