model

Llama 4 Maverick 17B-128E

modelactiveprovisionalllama-4-maverick-17b-128e-75f0cfb9·2 events·first seen 7d ago

Aliases: Llama 4 Maverick 17B-128E, Llama 4 Maverick 17B-128E Instruct

Co-occurring entities

More like this (12)

Llama 4 Scout 17B-16E Llama-4-Maverick Llama 1B Llama-3 Llama 3.2 90B Vision Llama 2 70B Llama 4 Scout Llama 3.2 11B Vision Llama 3.2 90B Vision-Instruct Llama-3.1-8B Llama 3.1 70B Llama-Krikri-8B

Recent events (2)

7Meta Llama·7d ago·source ↗

Meta releases Llama 4 Maverick 17B-128E multimodal instruct model on Hugging Face

Meta released Llama 4 Maverick, a 17B active parameter model with 128 experts (MoE architecture), as an image-text-to-text instruct model on Hugging Face. The model supports multimodal inputs and multiple languages including Arabic, German, and English. With 28K+ downloads and 493 likes shortly after release, it is seeing significant early adoption.

Frontier Model Releases Open Weights Progress Llama 4 Maverick 17B-128E Hugging Face Meta +1 more

7Meta Llama·7d ago·source ↗

Meta releases Llama 4 Maverick 17B-128E multimodal model on Hugging Face

Meta released Llama 4 Maverick, a 17B active parameter model with 128 experts (mixture-of-experts architecture), on Hugging Face. The model supports image-text-to-text tasks, making it a multimodal open-weights release. This is part of the Llama 4 generation, representing Meta's latest open-weights frontier push with MoE architecture.

Frontier Model Releases Open Weights Progress Llama 4 Maverick 17B-128E Hugging Face Meta +1 more