What are the hardware requirements for Marx 3B V3 GPTQ?

Marx 3B V3 GPTQ requires approximately 1.8 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 Marx 3B V3 GPTQ and how large is it?

Marx 3B V3 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 Marx 3B V3 GPTQ?

Marx 3B V3 GPTQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Marx 3B V3 GPTQ by TheBloke — VRAM 1.8GB, 4K context

Name: Marx 3B V3 GPTQ
Author: TheBloke

Marx 3B V3 GPTQ is an open-source language model by TheBloke. Features: 3b LLM, VRAM: 1.8GB, Context: 4K, License: cc-by-sa-4.0, Quantized, LLM Explorer Score: 0.09.

Arxiv:2305.14314 4-bit Base model:acrastt/marx-3b-v3 Base model:quantized:acrastt/m... Custom code Dataset:acrastt/everythinglm-v... En Gptq Quantized Region:us Safetensors Stablelm epoch

Model Card on HF 🤗: https://huggingface.co/TheBloke/Marx-3B-v3-GPTQ

Marx 3B V3 GPTQ Parameters and Internals

Model Type

text-generation

Supported Languages

English (high proficiency)

Training Details

Data Sources:

EverythingLM Data V3 (ShareGPT Format)

Methodology:

Finetuned for 2 epochs using QLoRA on EverythingLM Data V3 (ShareGPT Format)

Model Architecture:

StableLM 3B 4E1T

Input Output

Input Format:

User-Assistant format

Accepted Modalities:

text

Output Format:

Text generation

LLM Name	Marx 3B V3 GPTQ
Repository 🤗	https://huggingface.co/TheBloke/Marx-3B-v3-GPTQ
Model Name	Marx 3B V3
Model Creator	Bohan Du
Base Model(s)	Marx 3B V3 acrastt/Marx-3B-V3
Model Size	3b
Required VRAM	1.8 GB
Updated	2026-08-03
Maintainer	TheBloke
Model Type	stablelm_epoch
Model Files	1.8 GB
Supported Languages	en
GPTQ Quantization	Yes
Quantization Type	gptq
Model Architecture	StableLMEpochForCausalLM
License	cc-by-sa-4.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.34.1
Tokenizer Class	GPTNeoXTokenizerFast
Vocabulary Size	50304
Torch Data Type	float16

Rank the Marx 3B V3 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 Marx 3B V3 GPTQ

Best Alternatives	Context / RAM	Downloads	Likes
Stable Code 3B GPTQ	16K / 1.8 GB	10	12
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
Stable Code 3B Mlx	16K / 5.6 GB	17	1

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Marx-3B-v3-GPTQ.