What are the hardware requirements for Deepseek Coder 6.7B Instruct?

Deepseek Coder 6.7B Instruct requires approximately 13.5 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 Instruct and how large is it?

Deepseek Coder 6.7B Instruct is developed by deepseek-ai, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Deepseek Coder 6.7B Instruct perform on standard benchmarks?

Deepseek Coder 6.7B Instruct has the following published scores: MMLU 39.02, HumanEval (Python) 80.22. Compare against reference models on this page or on the LLM Explorer leaderboards.

Deepseek Coder 6.7B Instruct by deepseek-ai — VRAM 13.5GB, 16K context

Name: Deepseek Coder 6.7B Instruct
Rating: 3 (5 reviews)
Author: deepseek-ai

Deepseek Coder 6.7B Instruct is an open-source language model by deepseek-ai. Features: 7b LLM, VRAM: 13.5GB, Context: 16K, License: other, Instruction-Based, Code Generating, LLM Explorer Score: 0.23, Arc: 38.1, HellaSwag: 55.1, MMLU: 39, GSM8K: 26.8, HumanEval: 80.2.

Codegen Conversational Deploy:azure Endpoints compatible Instruct Llama Pytorch Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct

Deepseek Coder 6.7B Instruct Parameters and Internals

Model Type

code generation

Use Cases

Areas:

coding assistant, software development

Applications:

code completion, project-level code corpus analysis

Primary Use Cases:

code completion, code infilling

Supported Languages

English (fluent), Chinese (fluent)

Training Details

Data Sources:

2T tokens consisting of 87% code and 13% natural language in both English and Chinese

Data Volume:

2T tokens

Context Length:

16000

Input Output

Accepted Modalities:

text

LLM Name	Deepseek Coder 6.7B Instruct
Repository 🤗	https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct
Model Size	7b
Required VRAM	13.5 GB
Updated	2026-08-08
Maintainer	deepseek-ai
Model Type	llama
Instruction-Based	Yes
Model Files	10.0 GB: 1-of-2 3.5 GB: 2-of-2 10.0 GB: 1-of-2 3.5 GB: 2-of-2
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	other
Context Length	16384
Model Max Length	16384
Transformers Version	4.34.1
Tokenizer Class	LlamaTokenizerFast
Beginning of Sentence Token	<｜begin▁of▁sentence｜>
End of Sentence Token	<\|EOT\|>
Vocabulary Size	32256
Torch Data Type	bfloat16

Rank the Deepseek Coder 6.7B Instruct 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

Quantized Models of the Deepseek Coder 6.7B Instruct

Model	Likes	Downloads	VRAM
...epseek Coder 6.7B Instruct AWQ	19	291702	3 GB
...pseek Coder 6.7B Instruct GGUF	249	29540	2 GB
...pseek Coder 6.7B Instruct GGUF	8	2370	2 GB
...pseek Coder 6.7B Instruct GPTQ	25	514	3 GB

Best Alternatives to Deepseek Coder 6.7B Instruct

Best Alternatives	Context / RAM	Downloads	Likes
CodeLlama 7B Instruct Hf	16K / 13.5 GB	58587	258
GetCode Slerp	16K / 13.6 GB	87	1
Stack Codellama 7B Inst	16K / 13.5 GB	66	0
CodeV CL 7B	16K / 13.5 GB	430	1
CodeLlama 7B Instruct Hf	16K / 13.5 GB	2313	63
Glaive Coder 7B	16K / 27 GB	85	55
...deLlama 7B Instruct Hf 8bits Q	16K / 4.2 GB	17	1
Llama 2 7B Chat Finetune5	16K / 13.8 GB	3	1
...ama 7B Instruct Hf Dequantized	16K / 13.5 GB	197	0
CodeLLama SFT FILTERED	16K / 13.5 GB	9	0