RADAR ARCHIVE
Week 49, 2024
1 tool added to the directory, Dec 2 – 8, 2024.
Added to the directory (1)
Tested and written up.
Efficient 70B open model matching 405B quality
Llama 3.3 is Meta's 70B-parameter multilingual instruction-tuned model, released in December 2024. It delivers text-only performance comparable to the much larger Llama 3.1 405B model while running far more efficiently, with a 128K-token context window and broad language support.
Why: Llama 3.3 is the practical sweet spot in the Llama family: it gives users near-frontier open-model quality in a 70B package that is far cheaper to host and fine-tune than the 405B model.
Free
Best for Efficient Open LLMs
Visit