search
Get Started
search
DeepSeek Coder (via Ollama) - LLM
zoom_in Click to enlarge

DeepSeek Coder (via Ollama)

language

description DeepSeek Coder (via Ollama) Overview

DeepSeek Coder is highly regarded in academic circles for its strong performance across a wide array of programming languages. It often provides superior accuracy in understanding niche or complex language constructs. It's a fantastic choice for polyglot developers who frequently switch between languages like Rust, Go, and Python within the same project.

help DeepSeek Coder (via Ollama) FAQ

Which DeepSeek Coder sizes can I run through Ollama?

Ollama's original DeepSeek Coder library includes 1.3B, 6.7B, and 33B parameter variants. Their listed download sizes range from about 776 MB for 1.3B to 19 GB for 33B.

What command starts DeepSeek Coder in Ollama?

Run `ollama run deepseek-coder` for the default model or specify a tag such as `ollama run deepseek-coder:6.7b`. Ollama exposes local generation through its CLI and an HTTP API.

Does the original DeepSeek Coder support code infilling?

Yes, the model was trained with a fill-in-the-blank objective for completing code between existing sections. The original DeepSeek Coder family uses a 16K context window.

Should I use DeepSeek Coder or DeepSeek-Coder-V2 in Ollama?

DeepSeek-Coder-V2 is the newer family and expands claimed language support from 86 to 338 programming languages. It also offers up to a 128K context window, compared with 16K for the original DeepSeek Coder models.

Reviews & Comments

Write a Review

rate_review

Be the first to review

Share your thoughts with the community and help others make better decisions.

Save to your list

Save your favorites and follow how their scores change over time.

Save favorites
Get updates
Compare scores

Already have an account? Sign in

Compare Items

See how they stack up against each other

Comparing
VS
Select 1 more item to compare