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-vl2 logo
deepseek-vl2
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 27.0B ↓ 5.2K
DeepSeek-V2-Chat-0628 logo
DeepSeek-V2-Chat-0628
deepseek-ai

Model Download Evaluation Results Model Architecture API Platform License Citation

open-source ↓ 5K
deepseek-math-7b-instruct logo
deepseek-math-7b-instruct
deepseek-ai

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

open-source 7.0B ↓ 4.9K
deepseek-coder-33b-instruct logo
deepseek-coder-33b-instruct
deepseek-ai

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

code 33.0B ↓ 4.4K
DeepSeek-Coder-V2-Base logo
DeepSeek-Coder-V2-Base
deepseek-ai

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

code 236.0B ↓ 2.9K
deepseek-math-7b-base logo
deepseek-math-7b-base
deepseek-ai

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

reasoning 7.0B ↓ 2.7K
deepseek-coder-33b-base logo
deepseek-coder-33b-base
deepseek-ai

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

code 33.0B ↓ 1.7K
deepseek-math-7b-rl logo
deepseek-math-7b-rl
deepseek-ai

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

open-source 7.0B ↓ 1.3K
deepseek-llm-67b-chat logo
deepseek-llm-67b-chat
deepseek-ai

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

open-source 67.0B ↓ 1.1K
deepseek-coder-7b-base-v1.5 logo
deepseek-coder-7b-base-v1.5
deepseek-ai

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

code 7.0B ↓ 850
DeepSeek-Prover-V2-671B logo
DeepSeek-Prover-V2-671B
deepseek-ai

We introduce DeepSeek-Prover-V2, an open-source large language model designed for formal theorem proving in Lean 4, with initialization data collected through a recursive theorem proving pipeline powered by DeepSeek-V3. The cold-start training procedure begins by prompting DeepSe…

open-source 671.0B ↓ 707
DeepSeek-V2.5-1210 logo
DeepSeek-V2.5-1210
deepseek-ai

DeepSeek-V2.5-1210 is an upgraded version of DeepSeek-V2.5, with improvements across various capabilities:

open-source ↓ 701