What are the hardware requirements for Deepseek Coder 6.7B Base GGUF?

Deepseek Coder 6.7B Base GGUF requires approximately 2.8 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Deepseek Coder 6.7B Base GGUF and how large is it?

Deepseek Coder 6.7B Base GGUF is developed by TheBloke, a model with 6.7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Deepseek Coder 6.7B Base GGUF?

Deepseek Coder 6.7B Base GGUF is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Deepseek Coder 6.7B Base GGUF by TheBloke — VRAM 2.8GB

Name: Deepseek Coder 6.7B Base GGUF
Author: TheBloke

Deepseek Coder 6.7B Base GGUF is an open-source language model by TheBloke. Features: 6.7b LLM, VRAM: 2.8GB, License: other, Quantized, Code Generating, LLM Explorer Score: 0.13.

Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-... Codegen Deepseek Gguf Quantized Region:us

Model Card on HF 🤗: https://huggingface.co/TheBloke/deepseek-coder-6.7B-base-GGUF

Deepseek Coder 6.7B Base GGUF Parameters and Internals

Model Type

deepseek

Use Cases

Areas:

Coding, Software Development

Applications:

Code completion, Code insertion, Repository-level code completion

Primary Use Cases:

Generate code snippets, Fill in the blanks in code, Complete existing code projects

Additional Notes

The model supports project-level code completion and infilling tasks with a window size of 16K.

Supported Languages

English (Advanced), Chinese (Advanced)

Training Details

Data Sources:

Code and natural language data

Data Volume:

2T tokens

Methodology:

Pre-trained on project-level code corpus with 87% code and 13% natural language using a window size of 16K

Context Length:

16000

Model Architecture:

Multi-Head Attention

LLM Name	Deepseek Coder 6.7B Base GGUF
Repository 🤗	https://huggingface.co/TheBloke/deepseek-coder-6.7B-base-GGUF
Model Name	Deepseek Coder 6.7B Base
Model Creator	DeepSeek
Base Model(s)	deepseek-ai/deepseek-coder-6.7b-base deepseek-ai/deepseek-coder-6.7b-base
Model Size	6.7b
Required VRAM	2.8 GB
Updated	2026-08-08
Maintainer	TheBloke
Model Type	deepseek
Model Files	2.8 GB 3.6 GB 3.3 GB 3.0 GB 3.8 GB 4.1 GB 3.9 GB 4.7 GB 4.8 GB 4.7 GB 5.5 GB 7.2 GB
GGUF Quantization	Yes
Quantization Type	gguf
Generates Code	Yes
Model Architecture	AutoModel
License	other

Rank the Deepseek Coder 6.7B Base GGUF capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Deepseek Coder 6.7B Base GGUF

Best Alternatives	Context / RAM	Downloads	Likes
...pseek Coder 6.7B Instruct GGUF	0K / 2.8 GB	29540	249

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/deepseek-coder-6.7B-base-GGUF.