What are the hardware requirements for Deepseek Coder 5.7bmqa Base AWQ?

Deepseek Coder 5.7bmqa Base AWQ requires approximately 3.4 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 5.7bmqa Base AWQ and how large is it?

Deepseek Coder 5.7bmqa Base AWQ is developed by TheBloke, a model with 5.7b 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 5.7bmqa Base AWQ?

Deepseek Coder 5.7bmqa Base AWQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Deepseek Coder 5.7bmqa Base AWQ by TheBloke — VRAM 3.4GB, 16K context

Name: Deepseek Coder 5.7bmqa Base AWQ
Author: TheBloke

Deepseek Coder 5.7bmqa Base AWQ is an open-source language model by TheBloke. Features: 5.7b LLM, VRAM: 3.4GB, Context: 16K, License: other, Quantized, Code Generating, LLM Explorer Score: 0.09.

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

Model Card on HF 🤗: https://huggingface.co/TheBloke/deepseek-coder-5.7bmqa-base-AWQ

Deepseek Coder 5.7bmqa Base AWQ Parameters and Internals

Model Type

deepseek

Use Cases

Primary Use Cases:

code completion, code insertion, repository-level code completion

Supported Languages

en (English), zh (Chinese)

Training Details

Data Sources:

2 trillion tokens with 87% code and 13% linguistic data

Data Volume:

2T tokens

Context Length:

16000

Model Architecture:

Multi Query Attention

Input Output

Input Format:

{prompt}

LLM Name	Deepseek Coder 5.7bmqa Base AWQ
Repository 🤗	https://huggingface.co/TheBloke/deepseek-coder-5.7bmqa-base-AWQ
Model Name	Deepseek Coder 5.7Bmqa Base
Model Creator	DeepSeek
Base Model(s)	deepseek-ai/deepseek-coder-5.7bmqa-base deepseek-ai/deepseek-coder-5.7bmqa-base
Model Size	5.7b
Required VRAM	3.4 GB
Updated	2026-07-05
Maintainer	TheBloke
Model Type	deepseek
Model Files	3.4 GB
AWQ Quantization	Yes
Quantization Type	awq
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	float16

Rank the Deepseek Coder 5.7bmqa Base AWQ 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