Featured Tool

Llama 4

Latest Llama model family by Meta with Mixture-of-Experts architecture.

Open SourceSelf HostedOffline CapableGPU Required (16GB+ VRAM)
0.0 (0)

About

Llama 4 by Meta introduces Scout (17B active / 109B total) and Maverick (17B active / 400B total) variants using Mixture-of-Experts. Supports 10M+ context length (Scout), multimodal input, and 12 languages. Llama 4 Community License.

Reviews (0)

Leave a Review

No reviews yet. Be the first to review!

Details

Price
Free
Platform
Local/Desktop
Difficulty
Advanced (4/5)
License
Llama 4 Community
Minimum VRAM
16 GB
Added
Apr 3, 2026

Related Tools

Open-weight models by Google in 2B, 9B, and 27B sizes with strong performance.

Open SourceSelf HostedOfflineGPU 4GB+
Easy
0.0 (0)

Open-weight LLM by Meta in 8B and 70B sizes with strong general capabilities.

Open SourceSelf HostedOfflineGPU 8GB+
Intermediate
0.0 (0)
Featured

Open-weight LLM family by Alibaba with strong multilingual and coding abilities.

Open SourceSelf HostedOfflineGPU 8GB+
Intermediate
0.0 (0)

Small language model by Microsoft in 3.8B size with strong benchmark performance.

Open SourceSelf HostedOfflineGPU 4GB+
Easy
0.0 (0)

Open-access 176B parameter multilingual LLM by BigScience supporting 46 languages.

Open SourceSelf HostedOfflineGPU 80GB+
Expert
0.0 (0)

Retrieval-augmented generation optimized LLM by Cohere with 128K context.

Open SourceSelf HostedOfflineGPU 24GB+
Advanced
0.0 (0)
Browse all Large Language Models (LLMs) tools