What are the hardware requirements for Deepseek Coder 1.3B Base?

Deepseek Coder 1.3B Base requires approximately 2.7 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 1.3B Base and how large is it?

Deepseek Coder 1.3B Base is developed by deepseek-ai, 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.

How does Deepseek Coder 1.3B Base perform on standard benchmarks?

Deepseek Coder 1.3B Base has the following published scores: HumanEval (Python) 32.13. Compare against reference models on this page or on the LLM Explorer leaderboards.

Deepseek Coder 1.3B Base by deepseek-ai — VRAM 2.7GB, 16K context

Name: Deepseek Coder 1.3B Base
Rating: 3 (1 reviews)
Author: deepseek-ai

Deepseek Coder 1.3B Base is an open-source language model by deepseek-ai. Features: 1.3b LLM, VRAM: 2.7GB, Context: 16K, License: other, Code Generating, LLM Explorer Score: 0.13, HumanEval: 32.1.

Codegen Endpoints compatible Llama Pytorch Region:us

Model Card on HF 🤗: https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-base

Deepseek Coder 1.3B Base Parameters and Internals

Model Type

code completion, state-of-the-art

Use Cases

Areas:

research, commercial applications

Applications:

code completion, code inference

Supported Languages

English (high), Chinese (high)

Training Details

Data Sources:

87% code, 13% natural language

Data Volume:

2 trillion tokens

Methodology:

Multi-Head Attention, Project-level code corpus, Window size 16K, Fill-in-the-blank task

Context Length:

16000

Model Architecture:

Multi-Head Attention

Input Output

Accepted Modalities:

code

LLM Name	Deepseek Coder 1.3B Base
Repository 🤗	https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-base
Model Size	1.3b
Required VRAM	2.7 GB
Updated	2026-07-01
Maintainer	deepseek-ai
Model Type	llama
Model Files	2.7 GB
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	<｜end▁of▁sentence｜>
Vocabulary Size	32256
Torch Data Type	bfloat16

Rank the Deepseek Coder 1.3B Base 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 1.3B Base

Model	Likes	Downloads
Deepseek Coder 1.3B Base GGUF	9	3249
Deepseek Coder 1.3B Base AWQ	0	48
Deepseek Coder 1.3B Base GPTQ	2	12

Best Alternatives to Deepseek Coder 1.3B Base

Best Alternatives	Context / RAM	Downloads	Likes
Imagine V8	16K / 2.7 GB	702	1
Deepseek Coder 1.3B Instruct	16K / 2.7 GB	92255	176
Llm4decompile 1.3B V2	16K / 2.7 GB	1272	11
...1.3B Chat And Function Calling	16K / 2.7 GB	238	0
Speechless Coder Ds 1.3B	16K / 2.7 GB	180	0
Deepseek Coder 1.3B Chat	16K / 2.7 GB	98	1
...c Deepseek Coder 1.3B Instruct	16K / 5.4 GB	5	0
CursorCore DS 1.3B SR	16K / 2.7 GB	29	2
CursorCore DS 1.3B LC	16K / 2.7 GB	27	0
CursorCore DS 1.3B	16K / 2.7 GB	9	0

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