What are the hardware requirements for StableCode 3B?

StableCode 3B requires approximately 6.1 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed StableCode 3B and how large is it?

StableCode 3B is developed by rtlabs, a model with 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 StableCode 3B?

StableCode 3B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

StableCode 3B by rtlabs — VRAM 6.1GB, 4K context

Name: StableCode 3B
Author: rtlabs

StableCode 3B is an open-source language model by rtlabs. Features: 3b LLM, VRAM: 6.1GB, Context: 4K, License: apache-2.0, Code Generating, LLM Explorer Score: 0.08.

Arxiv:1910.02054 Arxiv:2104.09864 Code Codegen Dataset:bigcode/starcoderdata Endpoints compatible Gpt neox Model-index Pytorch Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/rtlabs/StableCode-3B

StableCode 3B Parameters and Internals

Model Type

code completion, causal-lm

Use Cases

Areas:

Software Development, Code Generation

Applications:

Code completion in IDEs

Primary Use Cases:

Single/multiline code completion up to 4k token context.

Limitations:

Not intended for unlawful content creation or activities with high risk of harm.

Considerations:

Use in conjunction with tools to attribute code outputs.

Additional Notes

Compatible with TabbyML using CTranslate2 format.

Supported Languages

code (Proficient in multiple programming languages.)

Training Details

Data Sources:

bigcode/starcoderdata

Data Volume:

300 billion tokens

Methodology:

Pre-trained on diverse set of programming languages using StarCoder tokenizer.

Context Length:

4096

Model Architecture:

3 billion parameter decoder-only model, utilizing GPT-NeoX framework, trained with mixed-precision BF16.

Input Output

Input Format:

Code snippets or text prompts

Accepted Modalities:

code

Output Format:

Code completion

LLM Name	StableCode 3B
Repository 🤗	https://huggingface.co/rtlabs/StableCode-3B
Model Size	3b
Required VRAM	6.1 GB
Updated	2026-08-02
Maintainer	rtlabs
Model Type	gpt_neox
Model Files	6.1 GB 6.1 GB
Supported Languages	code
Generates Code	Yes
Model Architecture	GPTNeoXForCausalLM
License	apache-2.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.30.2
Tokenizer Class	PreTrainedTokenizerFast
Vocabulary Size	49152
Torch Data Type	float16

Rank the StableCode 3B 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 StableCode 3B

Best Alternatives	Context / RAM	Downloads	Likes
Stablecode Completion Alpha 3B	16K / 14.1 GB	180	119
...blecode Completion Alpha 3B 4K	4K / 6.1 GB	434	278
Stablecode Instruct Alpha 3B	4K / 6.1 GB	2	304
...tion Alpha 3B 4K Openvino Int8	4K / 2.8 GB	8	1
...blecode Instruct Alpha 3B GPTQ	4K / 1.8 GB	10	17
...de Completion Alpha 3B 4K GPTQ	4K / 1.8 GB	6	9
...blecode Instruct Alpha 3B GPTQ	4K / 1.8 GB	5	1

Note: green Score (e.g. "73.2") means that the model is better than rtlabs/StableCode-3B.