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

Deepseek Coder 6.7B Base GPTQ requires approximately 3.9 GB of VRAM and supports a context window of 16K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

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

Deepseek Coder 6.7B Base GPTQ 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 GPTQ?

Deepseek Coder 6.7B Base GPTQ 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 GPTQ by TheBloke — VRAM 3.9GB, 16K context

Name: Deepseek Coder 6.7B Base GPTQ
Author: TheBloke

Deepseek Coder 6.7B Base GPTQ is an open-source language model by TheBloke. Features: 6.7b LLM, VRAM: 3.9GB, Context: 16K, License: other, Quantized, Code Generating, LLM Explorer Score: 0.09.

4-bit Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-... Codegen Gptq Llama Quantized Region:us Safetensors

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

Deepseek Coder 6.7B Base GPTQ Parameters and Internals

Model Type

deepseek

Use Cases

Areas:

research, commercial applications

Applications:

code completion, code insertion, repository level code completion

Supported Languages

English (high), Chinese (high)

Training Details

Data Sources:

project-level code corpus

Data Volume:

2T tokens

Methodology:

Trained from scratch with 87% code and 13% natural language using a window size of 16K and an extra fill-in-the-blank task

Context Length:

16000

Model Architecture:

Multi-Head Attention

Input Output

Input Format:

{prompt}

Accepted Modalities:

text

LLM Name	Deepseek Coder 6.7B Base GPTQ
Repository 🤗	https://huggingface.co/TheBloke/deepseek-coder-6.7B-base-GPTQ
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	3.9 GB
Updated	2026-05-21
Maintainer	TheBloke
Model Type	deepseek
Model Files	3.9 GB
GPTQ Quantization	Yes
Quantization Type	gptq
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	other
Context Length	16384
Model Max Length	16384
Transformers Version	4.35.0
Tokenizer Class	LlamaTokenizerFast
Beginning of Sentence Token	<｜begin▁of▁sentence｜>
End of Sentence Token	<｜end▁of▁sentence｜>
Vocabulary Size	32256
Torch Data Type	bfloat16

Rank the Deepseek Coder 6.7B Base GPTQ 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 GPTQ

Best Alternatives	Context / RAM	Downloads	Likes
...pseek Coder 6.7B Instruct GPTQ	16K / 3.9 GB	514	25
...rpreter DS 6.7B 6.0bpw H6 EXL2	16K / 5.2 GB	5	2
...rpreter DS 6.7B 8.0bpw H8 EXL2	16K / 6.9 GB	3	2
...rpreter DS 6.7B 4.0bpw H6 EXL2	16K / 3.6 GB	1	1
...Deepseek Coder 6.7B Energy Sft	16K / 13.5 GB	261	0
Deepseek Coder 6.7B Base	16K / 13.5 GB	54216	124
...epseek Coder 6.7B Instruct AWQ	16K / 3.9 GB	291702	19
Speechless Coder Ds 6.7B	16K / 13.5 GB	459	7
...s Coder6.7b Reflct Adamw Iter1	16K / 13.5 GB	475	0
...Coder6.7b Reflct Rmsprop Iter1	16K / 13.5 GB	95	0

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