DeepSeek-R1
DeepSeek's first-generation reasoning models. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning without supervised fine-tuning, demonstrated remarkable performance on reasoning.
open-source-llmfree
2500
Active
DeepSeek-V3
A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
275
Views
0
Likes
Jan 2026
Added
github.com
Website
Tags
open-source-llmfree
Editorial Review
About DeepSeek-V3
About DeepSeek-V3
A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
Key Features
- Powerful AI technology
- User-friendly interface
- Efficient workflow integration
- Continuous updates and improvements
Use Cases
DeepSeek-V3 is an excellent tool in the open-source-llm category, suitable for all users who need AI assistance.
Ready to try DeepSeek-V3?
Visit the official website to get started
Quick Info
- Website
- github.com
- Added
- 1/21/2026
- Published
- 1/21/2026
- Updated
- 9/10/2026
Have an AI tool to share?
Submit it to AI Dreamhub
Get your product in front of people actively exploring AI tools.
Submit Your ToolRelated Tools
Qwen3
Qwen3 is Alibaba's Apache-2.0 open-weight model family, now best understood as a reproducible 2025 generation rather than the current hosted default. This guide separates Qwen3-2507 from Qwen3.6 open models and Model Studio APIs, with deployment, cost, context, license, safety and competitor decisions.
Qwen3Qwen3.6Qwen open weights
3230
Llama 3
Llama3 is a large language model developed by Meta AI. It is the successor to Meta's Llama2 language model.
open-source-llmfree
2790
Mixtral
Mixtral is Mistral AI's Apache-2.0 sparse mixture-of-experts model family, including Mixtral 8x7B and 8x22B base and instruction variants. This independent guide explains routing, active versus total parameters, memory and serving costs, quantization, evaluation, safety and modern alternatives.
open-source-llmfree
2360