AI Agent Hub

LLM Models · deepseek-ai

Browse the world's large language models. Compare parameters, benchmarks, VRAM and more.

62 models from deepseek-ai Compare
DeepSeek-R1-0528-Qwen3-8B logo
DeepSeek-R1-0528-Qwen3-8B
deepseek-ai

The DeepSeek R1 model has undergone a minor version upgrade, with the current version being DeepSeek-R1-0528. In the latest update, DeepSeek R1 has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introdu…

reasoning 8.0B ↓ 1M
deepseek-coder-7b-instruct-v1.5 logo
deepseek-coder-7b-instruct-v1.5
deepseek-ai

[🏠Homepage] [🤖 Chat with DeepSeek Coder] [Discord] [Wechat(微信)]

code 7.0B ↓ 812.8K
DeepSeek-Coder-V2-Lite-Instruct logo
DeepSeek-Coder-V2-Lite-Instruct
deepseek-ai

DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence

code ↓ 717.8K
DeepSeek-R1-Distill-Qwen-32B logo
DeepSeek-R1-Distill-Qwen-32B
deepseek-ai

We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrated remarkable performance on reasoning. With R…

reasoning 32.0B ↓ 577.8K
DeepSeek-R1-Distill-Qwen-1.5B logo
DeepSeek-R1-Distill-Qwen-1.5B
deepseek-ai

We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrated remarkable performance on reasoning. With R…

reasoning 1.5B ↓ 488.7K
DeepSeek-R1-Distill-Qwen-14B logo
DeepSeek-R1-Distill-Qwen-14B
deepseek-ai

We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrated remarkable performance on reasoning. With R…

reasoning 14.0B ↓ 460.1K
DeepSeek-V2-Lite-Chat logo
DeepSeek-V2-Lite-Chat
deepseek-ai

Model Download Evaluation Results Model Architecture API Platform License Citation

open-source ↓ 396.7K
deepseek-coder-6.7b-instruct logo
deepseek-coder-6.7b-instruct
deepseek-ai

[🏠Homepage] [🤖 Chat with DeepSeek Coder] [Discord] [Wechat(微信)]

code 6.7B ↓ 396.1K
DeepSeek-R1-Distill-Llama-8B logo
DeepSeek-R1-Distill-Llama-8B
deepseek-ai

We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrated remarkable performance on reasoning. With R…

reasoning 8.0B ↓ 388.6K
DeepSeek-R1-Distill-Qwen-7B logo
DeepSeek-R1-Distill-Qwen-7B
deepseek-ai

We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrated remarkable performance on reasoning. With R…

reasoning 7.0B ↓ 374K
DeepSeek-V2-Lite logo
DeepSeek-V2-Lite
deepseek-ai

Model Download Evaluation Results Model Architecture API Platform License Citation

open-source ↓ 368.6K
deepseek-vl2-tiny logo
deepseek-vl2-tiny
deepseek-ai

Introducing DeepSeek-VL2, an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon its predecessor, DeepSeek-VL. DeepSeek-VL2 demonstrates superior capabilities across various tasks, including but not limited to visual question…

multimodal 3.37B ↓ 265.9K