What are the hardware requirements for Stable Code 3B GPTQ?

Stable Code 3B GPTQ requires approximately 1.8 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 Stable Code 3B GPTQ and how large is it?

Stable Code 3B GPTQ is developed by TheBloke, 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 Stable Code 3B GPTQ?

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

Stable Code 3B GPTQ by TheBloke — VRAM 1.8GB, 16K context

Name: Stable Code 3B GPTQ
Author: TheBloke

Stable Code 3B GPTQ is an open-source language model by TheBloke. Features: 3b LLM, VRAM: 1.8GB, Context: 16K, License: other, Quantized, LLM Explorer Score: 0.11.

Arxiv:1910.02054 Arxiv:2104.09864 Arxiv:2204.06745 Arxiv:2305.06161 Arxiv:2307.09288 Arxiv:2309.12284 Arxiv:2310.10631 4-bit Base model:quantized:stability... Base model:stabilityai/stable-... Code Custom code Dataset:bigcode/commitpackft Dataset:bigcode/starcoderdata Dataset:bigcode/the-stack-gith... Dataset:eleutherai/proof-pile-... Dataset:meta-math/metamathqa Dataset:tiiuae/falcon-refinedw... En Gptq Model-index Quantized Region:us Safetensors Stablelm epoch

Model Card on HF 🤗: https://huggingface.co/TheBloke/stable-code-3b-GPTQ

Stable Code 3B GPTQ Parameters and Internals

Model Type

stablelm_epoch

Additional Notes

The model supports long contexts and is trained for Fill in the Middle (FIM) capabilities. It uses a modified version of the GPTNeoX Tokenizer.

Supported Languages

languages_supported (English, Code), proficiency_level (State-of-the-art performance on MultiPL-E metrics across multiple programming languages)

Training Details

Data Sources:

tiiuae/falcon-refinedweb, bigcode/the-stack-github-issues, bigcode/commitpackft, bigcode/starcoderdata, EleutherAI/proof-pile-2, meta-math/MetaMathQA

Data Volume:

1.3 trillion tokens

Context Length:

16384

Hardware Used:

256 NVIDIA A100 40GB GPUs

Model Architecture:

Decoder-only transformer similar to LLaMA architecture

LLM Name	Stable Code 3B GPTQ
Repository 🤗	https://huggingface.co/TheBloke/stable-code-3b-GPTQ
Model Name	Stable Code 3B
Model Creator	Stability AI
Base Model(s)	Stable Code 3B stabilityai/stable-code-3b
Model Size	3b
Required VRAM	1.8 GB
Updated	2026-07-13
Maintainer	TheBloke
Model Type	stablelm_epoch
Model Files	1.8 GB
Supported Languages	en
GPTQ Quantization	Yes
Quantization Type	gptq
Model Architecture	StableLMEpochForCausalLM
License	other
Context Length	16384
Model Max Length	16384
Transformers Version	4.37.0.dev0
Tokenizer Class	GPTNeoXTokenizer
Vocabulary Size	50304
Torch Data Type	bfloat16

Rank the Stable Code 3B GPTQ 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 Stable Code 3B GPTQ

Best Alternatives	Context / RAM	Downloads	Likes
Zephyr Quiklang 3B GPTQ	4K / 1.8 GB	13	1
Zephyr Quiklang 3B 4K GPTQ	4K / 1.8 GB	2	2
Dopeystableplats 3B V1 GPTQ	4K / 1.8 GB	6	0
Stablelm Zephyr 3B GPTQ	4K / 1.8 GB	10	12
...ling Stable Lm 3B 4e1t V0 GPTQ	4K / 1.8 GB	4	1
Rocket 3B GPTQ	4K / 1.8 GB	8	0
Nous Capybara 3B V1.9 GPTQ	4K / 1.8 GB	8	8
Akins 3B GPTQ	4K / 1.8 GB	6	2
Marx 3B V3 GPTQ	4K / 1.8 GB	5	2
Stable Code 3B Mlx	16K / 5.6 GB	17	1