THE MODEL DIRECTORY

Every listing. A closer look.

2,841 catalog records, ordered by name. Each profile has its own link and shows where the information came from. 717 repeat listings (training checkpoints, adapters, other formats and duplicate cloud entries, each shown on its main model’s page) and listings with no published task, size, or price are left out unless you search for them. Show all 3,558

Models A–Z

Page 11 of 60 · Coverage limits

DeepSeek · Downloadable

deepseek-coder-6.7b-base

Text generationCoding

Designed for coding and software tasks. Generates text for conversations and writing.

Listed 6.7B parameters

DeepSeek · Downloadable

deepseek-coder-6.7b-instruct

Text generationCoding

Designed for coding and software tasks. Generates text for conversations and writing.

Listed 6.7B parameters

JetBrains · Downloadable

deepseek-coder-6.7B-kexer

Text generationCoding

Designed for coding and software tasks. Generates text for conversations and writing.

Listed 6.7B parameters

DeepSeek · Downloadable

deepseek-coder-7b-base-v1.5

Text generationCoding

Designed for coding and software tasks. Generates text for conversations and writing.

Listed 7B parameters

DeepSeek · Downloadable

deepseek-coder-7b-instruct-v1.5

Text generationCoding

Designed for coding and software tasks. Generates text for conversations and writing.

Listed 7B parameters

DeepSeek · Downloadable

DeepSeek-Coder-V2-Base

Text generationCoding

Designed for coding and software tasks. Generates text for conversations and writing.

Listed 236B parameters

DeepSeek · Downloadable

DeepSeek-Coder-V2-Instruct

Text generationCoding

Designed for coding and software tasks. Generates text for conversations and writing.

Listed 236B parameters

DeepSeek · Downloadable

DeepSeek-Coder-V2-Instruct-0724

Text generationCoding

Designed for coding and software tasks. Generates text for conversations and writing.

Listed 236B parameters

DeepSeek · Downloadable

DeepSeek-Coder-V2-Lite-Base

Text generationCoding

Designed for coding and software tasks. Generates text for conversations and writing.

Listed 16B parameters

DeepSeek · Downloadable

DeepSeek-Coder-V2-Lite-Instruct

Text generationCoding

Designed for coding and software tasks. Generates text for conversations and writing.

Listed 16B parameters

DeepSeek · Downloadable

deepseek-llm-67b-base

Text generation

Generates text for conversations and writing.

Listed 67B parameters

DeepSeek · Downloadable

deepseek-llm-67b-chat

Text generation

Generates text for conversations and writing.

Listed 67B parameters

DeepSeek · Downloadable

deepseek-llm-7b-base

Text generation

Generates text for conversations and writing.

Listed 7B parameters

DeepSeek · Downloadable

deepseek-llm-7b-chat

Text generation

Generates text for conversations and writing.

Listed 7B parameters

DeepSeek · Downloadable

deepseek-math-7b-base

Text generation

Generates text for conversations and writing.

Listed 7B parameters

DeepSeek · Downloadable

deepseek-math-7b-rl

Text generation

Generates text for conversations and writing.

Listed 7B parameters

DeepSeek · Downloadable

DeepSeek-Math-V2

Text generation

Generates text for conversations and writing.

Listed 685B parameters

DeepSeek · Downloadable

deepseek-moe-16b-base

Text generation

Generates text for conversations and writing.

Listed 16B parameters

DeepSeek · Downloadable

deepseek-moe-16b-chat

Text generation

Generates text for conversations and writing.

Listed 16B parameters

DeepSeek · Downloadable

DeepSeek-OCR

VisionDocument readingEmbeddings

Understands text and images and responds in text.

Listed 3.3B parameters

DeepSeek · Downloadable

DeepSeek-OCR-2

VisionDocument readingEmbeddings

Understands text and images and responds in text.

Listed 3.4B parameters

DeepSeek · Downloadable

DeepSeek-Prover-V1

Text generation

Generates text, according to its published model architecture (LlamaForCausalLM). No task is listed on Hugging Face, so check the model card for intended use.

Listed 6.9B parameters

DeepSeek · Downloadable

DeepSeek-Prover-V1.5-Base

Text generation

Generates text, according to its published model architecture (LlamaForCausalLM). No task is listed on Hugging Face, so check the model card for intended use.

Listed 6.9B parameters

DeepSeek · Downloadable

DeepSeek-Prover-V1.5-RL

Text generation

Generates text, according to its published model architecture (LlamaForCausalLM). No task is listed on Hugging Face, so check the model card for intended use.

Listed 6.9B parameters

DeepSeek · Downloadable

DeepSeek-Prover-V1.5-SFT

Text generation

Generates text, according to its published model architecture (LlamaForCausalLM). No task is listed on Hugging Face, so check the model card for intended use.

Listed 6.9B parameters

DeepSeek · Downloadable

DeepSeek-Prover-V2-671B

Text generation

Generates text for conversations and writing.

Listed 671B parameters

DeepSeek · Downloadable

DeepSeek-Prover-V2-7B

Text generation

Generates text, according to its published model architecture (LlamaForCausalLM). No task is listed on Hugging Face, so check the model card for intended use.

Listed 7B parameters

DeepSeek · Downloadable

DeepSeek-R1

Text generationReasoning

Generates text for conversations and writing. Supports a reasoning mode.

Listed 684B parameters

DeepSeek · Downloadable

DeepSeek-R1-0528

Text generationReasoning

Generates text for conversations and writing. Supports a reasoning mode.

Listed 685B parameters

DeepSeek · Downloadable

DeepSeek-R1-0528-Qwen3-8B

Text generationReasoning

Generates text for conversations and writing. Supports a reasoning mode.

Listed 8B parameters

DeepSeek · Downloadable

DeepSeek-R1-Distill-Llama-70B

Text generationReasoning

Generates text for conversations and writing. Supports a reasoning mode.

Listed 70B parameters

DeepSeek · Downloadable

DeepSeek-R1-Distill-Llama-8B

Text generationReasoning

Generates text for conversations and writing. Supports a reasoning mode.

Listed 8B parameters

DeepSeek · Downloadable

DeepSeek-R1-Distill-Qwen-1.5B

Text generationReasoning

Generates text for conversations and writing. Supports a reasoning mode.

Listed 1.5B parameters

DeepSeek · Downloadable

DeepSeek-R1-Distill-Qwen-14B

Text generationReasoning

Generates text for conversations and writing. Supports a reasoning mode.

Listed 14B parameters

DeepSeek · Downloadable

DeepSeek-R1-Distill-Qwen-32B

Text generationReasoning

Generates text for conversations and writing. Supports a reasoning mode.

Listed 32B parameters

DeepSeek · Downloadable

DeepSeek-R1-Distill-Qwen-7B

Text generationReasoning

Generates text for conversations and writing. Supports a reasoning mode.

Listed 7B parameters

DeepSeek · Downloadable

DeepSeek-R1-Zero

Text generationReasoning

Generates text for conversations and writing. Supports a reasoning mode.

Listed 685B parameters

DeepSeek · Downloadable

DeepSeek-V2

Text generation

Generates text for conversations and writing.

Listed 236B parameters

DeepSeek · Downloadable

DeepSeek-V2-Chat

Text generation

Generates text for conversations and writing.

Listed 236B parameters

DeepSeek · Downloadable

DeepSeek-V2-Chat-0628

Text generation

Generates text for conversations and writing.

Listed 236B parameters

DeepSeek · Downloadable

DeepSeek-V2-Lite

Text generation

Generates text for conversations and writing.

Listed 16B parameters

DeepSeek · Downloadable

DeepSeek-V2-Lite-Chat

Text generation

Generates text for conversations and writing.

Listed 16B parameters

DeepSeek · Downloadable

DeepSeek-V2.5

Text generation

Generates text for conversations and writing.

Listed 236B parameters

DeepSeek · Downloadable

DeepSeek-V2.5-1210

Text generation

Generates text for conversations and writing.

Listed 236B parameters

DeepSeek · Downloadable

DeepSeek-V3

Text generation

Generates text for conversations and writing.

Listed 685B parameters

DeepSeek · Downloadable

DeepSeek-V3-0324

Text generation

Generates text for conversations and writing.

Listed 685B parameters

DeepSeek · Downloadable

DeepSeek-V3-Base

Text generation

Generates text, according to its published model architecture (DeepseekV3ForCausalLM). No task is listed on Hugging Face, so check the model card for intended use.

Listed 685B parameters

Listing dates are source catalog dates, not verified public releases. This growing library does not yet cover every released model.