What are the hardware requirements for Deepseek Coder 33B Base GGUF?

Deepseek Coder 33B Base GGUF requires approximately 14 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Deepseek Coder 33B Base GGUF and how large is it?

Deepseek Coder 33B Base GGUF is developed by TheBloke, a model with 33b 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 33B Base GGUF?

Deepseek Coder 33B 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 33B Base GGUF by TheBloke — VRAM 14GB

Name: Deepseek Coder 33B Base GGUF
Author: TheBloke

Deepseek Coder 33B Base GGUF is an open-source language model by TheBloke. Features: 33b LLM, VRAM: 14GB, License: other, Quantized, Code Generating, LLM Explorer Score: 0.11.

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-33B-base-GGUF

Deepseek Coder 33B Base GGUF Parameters and Internals

Model Type

deepseek

Use Cases

Applications:

coding tasks, project-level code completion, code infilling

Additional Notes

Supports project-level code completion and infilling tasks. Enables users to choose between model sizes from 1B to 33B versions.

Supported Languages

English (13%), Chinese (13%), Code (87%)

Training Details

Data Sources:

2T tokens with 87% code and 13% linguistic data in both English and Chinese languages

Data Volume:

2 trillion tokens

Methodology:

Trained from scratch with project-level code corpus. Includes fill-in-the-blank task.

Context Length:

16000

Model Architecture:

Grouped-Query Attention

Input Output

Input Format:

{prompt}

LLM Name	Deepseek Coder 33B Base GGUF
Repository 🤗	https://huggingface.co/TheBloke/deepseek-coder-33B-base-GGUF
Model Name	Deepseek Coder 33B Base
Model Creator	DeepSeek
Base Model(s)	Deepseek Coder 33B Base deepseek-ai/deepseek-coder-33b-base
Model Size	33b
Required VRAM	14 GB
Updated	2026-08-03
Maintainer	TheBloke
Model Type	deepseek
Model Files	14.0 GB 17.6 GB 16.1 GB 14.4 GB 18.8 GB 19.9 GB 18.9 GB 23.0 GB 23.5 GB 23.0 GB 27.4 GB 35.4 GB
GGUF Quantization	Yes
Quantization Type	gguf
Generates Code	Yes
Model Architecture	AutoModel
License	other

Rank the Deepseek Coder 33B 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 33B Base GGUF

Best Alternatives	Context / RAM	Downloads	Likes
...epseek Coder 33B Instruct GGUF	0K / 14 GB	15508	196
Everyone Coder 33B Base GGUF	0K / 12.4 GB	728	13
Vicuna 33B Coder GGUF	0K / 13.5 GB	462	6

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/deepseek-coder-33B-base-GGUF.