Deepseek R1 is a locally installable Ollama model from the DeepSeek series. Agent Mag tracks its local install command, available tags, modalities, and runtime details on this page.

How do you use Deepseek R1?

Deepseek R1 can be installed locally with npx agentmag add model deepseek-r1, which wraps ollama pull deepseek-r1. This page also includes local Ollama run and API examples.

Deepseek R1 is listed as a local Ollama model. There is no hosted token price in Agent Mag; local compute and storage requirements depend on the tag you pull.

Deepseek R1

All models

DeepSeekDeepSeekLocal runtimeFree

Deepseek R1

160K context

Ollama install

35 tags

Deepseek R1 is available through Ollama for local agent workflows, with support for text input. DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.

What is Deepseek R1?

Deepseek R1 is a local model entry from Ollama that Agent Mag tracks for install commands, available tags, modalities, and agent workflow fit. Builders can install it with the Agent Mag CLI and run it through Ollama on their own machine.

Agent Mag install

Ollama model ID

DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.

Modalities

Input

text

Output

text

Ollama Tags

Tag	Size	Context	Input
deepseek-r1:latest	5.2GB	128K	text
deepseek-r1:1.5b	1.1GB	128K	text
deepseek-r1:7b	4.7GB	128K	text
deepseek-r1:8b	5.2GB	128K	text
deepseek-r1:14b	9.0GB	128K	text
deepseek-r1:32b	20GB	128K	text
deepseek-r1:70b	43GB	128K	text
deepseek-r1:671b	404GB	160K	text

Related local models

Deepseek V4 Flash

LocalOllama

DeepSeek-V4-Flash is a preview of the DeepSeek-V4 series, a Mixture-of-Experts model with 284B total parameters and 13B activated, built for efficient reasoning across a 1M-token context window.

Deepseek OCR

3bOllama

DeepSeek-OCR is a vision-language model that can perform token-efficient OCR.

Deepseek V3.2

LocalOllama

DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance.

Deepseek V3.1

671bOllama

DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode.

Stay in the know

Deepseek R1

What is Deepseek R1?

Related local models

Related content