What are the hardware requirements for Deepseek Coder 1.3B Instruct AWQ?

Deepseek Coder 1.3B Instruct AWQ requires approximately 0.9 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Deepseek Coder 1.3B Instruct AWQ and how large is it?

Deepseek Coder 1.3B Instruct AWQ is developed by TheBloke, a model with 1.3b 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 1.3B Instruct AWQ?

Deepseek Coder 1.3B Instruct AWQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Deepseek Coder 1.3B Instruct AWQ by TheBloke — VRAM 0.9GB, 8K context

Name: Deepseek Coder 1.3B Instruct AWQ
Author: TheBloke

Deepseek Coder 1.3B Instruct AWQ is an open-source language model by TheBloke. Features: 1.3b LLM, VRAM: 0.9GB, Context: 8K, License: other, Quantized, Instruction-Based, Code Generating, LLM Explorer Score: 0.09.

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

Model Card on HF 🤗: https://huggingface.co/TheBloke/deepseek-coder-1.3b-instruct-AWQ

Deepseek Coder 1.3B Instruct AWQ Parameters and Internals

Model Type

deepseek

Use Cases

Areas:

Research, Commercial applications

Applications:

AI programming assistance, Code completion

Primary Use Cases:

Project-level code completion, Infilling tasks

Limitations:

Can only answer computer science related questions, Refuses politically sensitive or non-CS questions

Considerations:

Model is designed specifically for computer science queries

Supported Languages

en (high), zh (high)

Training Details

Data Sources:

Project-level code corpus

Data Volume:

2T tokens, including 87% code and 13% linguistic data in English and Chinese

Methodology:

Fine-tuned on 2B tokens of instruction data with fill-in-the-blank task for code completion

Context Length:

16000

Input Output

Input Format:

Instruction based prompts

Accepted Modalities:

text

Output Format:

Text responses

LLM Name	Deepseek Coder 1.3B Instruct AWQ
Repository 🤗	https://huggingface.co/TheBloke/deepseek-coder-1.3b-instruct-AWQ
Model Name	Deepseek Coder 1.3B Instruct
Model Creator	DeepSeek
Base Model(s)	deepseek-ai/deepseek-coder-1.3b-instruct deepseek-ai/deepseek-coder-1.3b-instruct
Model Size	1.3b
Required VRAM	0.9 GB
Updated	2026-06-30
Maintainer	TheBloke
Model Type	deepseek
Instruction-Based	Yes
Model Files	0.9 GB
AWQ Quantization	Yes
Quantization Type	awq
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	other
Context Length	8192
Model Max Length	8192
Transformers Version	4.35.0
Tokenizer Class	LlamaTokenizerFast
Beginning of Sentence Token	<｜begin▁of▁sentence｜>
End of Sentence Token	<\|EOT\|>
Vocabulary Size	32256
Torch Data Type	float16

Rank the Deepseek Coder 1.3B Instruct 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

Best Alternatives to Deepseek Coder 1.3B Instruct AWQ

Best Alternatives	Context / RAM	Downloads	Likes
Deepseek Coder 1.3B Instruct	16K / 2.7 GB	92255	176
Speechless Coder Ds 1.3B	16K / 2.7 GB	180	0
...c Deepseek Coder 1.3B Instruct	16K / 5.4 GB	5	0
Hpc Coder V2.1.3B	16K / 2.7 GB	15	5
... 1.3B Instruct Trt Int4 G64 Hf	16K / 0.9 GB	7	0
...t Structured Output Peft Merge	16K / 2.7 GB	14	0
Datascience Coder 1.3B	16K / 2.7 GB	6	1
...pseek Coder 1.3B Instruct GPTQ	16K / 0.9 GB	91	7
...Coder 1.3B Function Calling V1	16K / 2.7 GB	457	2

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/deepseek-coder-1.3b-instruct-AWQ.