|
|
|
|
|
|
by lhl
995 days ago
|
|
|
While the llama2-34b base model hasn't been released, CodeLlama2 is effectively a fine-tuned version of 34b and there are some people working with that. As Ollama uses a llama.cpp fork on the backend, I'd expect its memory usage to be very similar to that. |
|
|