Llama 3 8B Lunaris

A smaller, earlier-generation 8-billion-parameter model from Sao10K based on Llama 3, with an 8192-token context window.

Strengths

Runs quickly and with low resource overhead while retaining instruction-following capability across general tasks.

Best for

Latency-sensitive applications and edge deployments where inference speed matters more than reasoning depth; earlier alternative to the newer Hanami and Euryale models in Sao10K's lineup.

Limitations

Limited context window compared to Sao10K's other offerings and less capable at extended reasoning or creative tasks than the larger 70-parameter models designed for roleplay and narrative work.