Featured Tool

DeepSeek-V3

High-performance open-weight MoE LLM with 671B total parameters.

Open SourceSelf HostedOffline CapableGPU Required (24GB+ VRAM)
0.0 (0)

About

DeepSeek-V3 is an open-weight Mixture-of-Experts language model with 671 billion total parameters and 37 billion active per token. It uses Multi-head Latent Attention and the DeepSeekMoE architecture with an auxiliary-loss-free load-balancing strategy and a multi-token prediction objective, and trains efficiently with FP8 mixed precision. It is competitive with leading proprietary models on benchmarks. Released under the DeepSeek 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
DeepSeek License
Minimum VRAM
24 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