DeepSeek Coder 6.7B Instruct

Create superiror code with advanced completion and infilling tasks.

Choose from hundreds of open-source LLMs in our model directory.

DeepSeek Coder 6.7B Instruct is a language model designed for code-related tasks. It’s trained with 87% code data, making it great for project-level completion and infilling.

Context window(in thousands)16384

Use cases for DeepSeek Coder 6.7B Instruct

  1. Code Generation: Automate code creation for various programming languages with high efficiency and accuracy.
  2. Bug Detection: Spot and suggest fixes for code bugs, boosting software reliability.
  3. Documentation: Generate detailed code documentation to improve maintainability and knowledge sharing.
Arena EloN/A
MT BenchN/A

DeepSeek Coder 6.7B Instruct, like GPT-3.5 Turbo-0301, isn't ranked on the LLM Leaderboard.

GPT-4 Omni


GPT-4 1106 Preview


GPT-4 0125 Preview


Llama 3 Instruct (70B)


GPT-4 0314


Throughput(output tokens per second)18
Latency(seconds to first tokens chunk received)0.2
Total Response Time(seconds to output 100 tokens)7.7

Expect slow throughput paired with low latency and slow total response time. This model may struggle in scenarios needing immediate feedback or high-speed processing.

What's Twitter saying?

  • SambaNova Systems Hosts New Code Generation Models: SambaNova Systems has announced that their Samba-1 platform will include code generation models from DeepSeek AI, such as deepseek-coder-6.7b-instruct and deepseek-coder-33b-instruct. These models outperform others on benchmarks like MBPP and LeetCode Contest. For more details, check out the paper on arxiv or the checkpoints on Hugging Face. Join their Discord for discussions. (Source: @SambaNovaAI)
  • Code Repository and Quantized Versions Available: Find the code repository on GitHub and access the 4-bit quantized version on Hugging Face. Make sure to remove quotes from the URLs for correct access. (Source: @trading_indian)

Explore Our LLM Library

Discover the power and diversity of large language models available with Telnyx. Explore the options below to find the perfect model for your project.


Chat with an LLM

Powered by our own GPU infrastructure, select a large language model, add a prompt, and chat away. For unlimited chats, sign up for a free account on our Mission Control Portal here.

Sign-up to get started with the Telnyx model library

Get started

Check out our helpful tools to help get you started.

  • Icon Resources EBook

    Test in the portal

    Easily browse and select your preferred model in the AI Playground.

  • Icon Resources Docs

    Explore the docs

    Don’t wait to scale, start today with our public API endpoints.

  • Icon Resources Article

    Stay up to date

    Keep an eye on our AI changelog so you don't miss a beat.

Start building your future with Telnyx AI

What is DeepSeek Coder?

DeepSeek Coder is a state-of-the-art code language model developed by DeepSeek AI, designed for high-performance code completion and infilling tasks. It is trained on 2T tokens, comprising 87% code from various programming languages and 13% natural language in both English and Chinese, available in multiple sizes ranging from 1.3B to 33B parameters.

How can I use DeepSeek Coder for my project?

To use DeepSeek Coder, you can integrate it into your project using the Hugging Face Transformers library. First, install the library, then load the model and tokenizer with the provided model name "deepseek-ai/deepseek-coder-6.7b-instruct". You can then input your code requirements, and the model will assist with code completion and infilling tasks. For detailed usage instructions, refer to the model's homepage.

Is DeepSeek Coder suitable for commercial projects?

Yes, DeepSeek Coder supports commercial use under its Model License. The code repository is licensed under the MIT License, ensuring flexibility and freedom for commercial and private projects alike. For more details, review the LICENSE-MODEL.

Can DeepSeek Coder be used for languages other than English?

Yes, DeepSeek Coder is trained on a dataset that includes both English and Chinese natural languages, making it suitable for code completion tasks in projects that involve these languages. It's designed to understand and generate code based on the context provided in either language.

How does DeepSeek Coder perform compared to other code models?

DeepSeek Coder achieves state-of-the-art performance among publicly available code models, outperforming others on several benchmarks, including HumanEval, MultiPL-E, MBPP, DS-1000, and APPS. Its training on a large corpus of 2T tokens with a significant percentage of code ensures superior model performance for a wide range of programming languages.

What model sizes are available for DeepSeek Coder?

DeepSeek Coder is available in various sizes to suit different project requirements and computational capabilities, including 1.3B, 5.7B, 6.7B, and 33B parameter models. This flexibility allows users to select the most suitable model size for their specific needs.

How do I report an issue or get support for DeepSeek Coder?

If you encounter any issues or have questions regarding DeepSeek Coder, you can raise an issue through the Hugging Face repository or contact the DeepSeek team directly at [email protected]. The team is dedicated to providing support and ensuring users can effectively utilize the model for their coding projects.

Is the model too large for serverless deployment?

The 6.7B parameter model of DeepSeek Coder is too large for serverless deployment through the Hugging Face Inference API. However, it can be launched on dedicated Inference Endpoints (like Telnyx), offering a scalable and flexible solution for integrating the model into your applications.