What are the hardware requirements for Mpt 7B Storywriter 4bit 128g?

Mpt 7B Storywriter 4bit 128g requires approximately 3.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Mpt 7B Storywriter 4bit 128g and how large is it?

Mpt 7B Storywriter 4bit 128g is developed by 4bit, a model with 7b 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 Mpt 7B Storywriter 4bit 128g?

Mpt 7B Storywriter 4bit 128g is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Mpt 7B Storywriter 4bit 128g by 4bit — VRAM 3.9GB

Name: Mpt 7B Storywriter 4bit 128g
Author: 4bit

Mpt 7B Storywriter 4bit 128g is an open-source language model by 4bit. Features: 7b LLM, VRAM: 3.9GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.07.

Arxiv:2108.12409 Arxiv:2205.14135 4bit Composer Custom code Dataset:the pile books3 Llm-foundry Mosaicml Mpt Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/4bit/mpt-7b-storywriter-4bit-128g

Mpt 7B Storywriter 4bit 128g Parameters and Internals

Model Type

text generation, story writing

Use Cases

Areas:

research, story writing

Applications:

fiction writing, literature generation

Primary Use Cases:

long context story writing

Limitations:

can produce factually incorrect output, may generate offensive outputs

Considerations:

MPT-7B-StoryWriter was trained on various public datasets; awareness of potential biases is needed.

Additional Notes

MPT-7B-StoryWriter can extrapolate even beyond 65k tokens using ALiBi to achieve generated texts up to 84k tokens.

Supported Languages

languages_supported ()

Training Details

Data Sources:

the_pile_books3

Methodology:

Finetuning with a context length of 65k tokens on a filtered fiction subset of the Books3 dataset

Context Length:

65536

Hardware Used:

8 A100-80GB GPUs

Model Architecture:

Modified decoder-only transformer with FlashAttention and ALiBi

LLM Name	Mpt 7B Storywriter 4bit 128g
Repository 🤗	https://huggingface.co/4bit/mpt-7b-storywriter-4bit-128g
Model Size	7b
Required VRAM	3.9 GB
Updated	2026-08-25
Maintainer	4bit
Model Type	mpt
Model Files	3.9 GB
Quantization Type	4bit
Model Architecture	MPTForCausalLM
License	apache-2.0
Model Max Length	65536
Transformers Version	4.28.1
Tokenizer Class	GPTNeoXTokenizer
Vocabulary Size	50432
Torch Data Type	bfloat16

Rank the Mpt 7B Storywriter 4bit 128g 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 Mpt 7B Storywriter 4bit 128g

Best Alternatives	Context / RAM	Downloads	Likes
Mpt 7B Chat Q8	0K / 6.9 GB	17	1
Mpt 7B Storywriter Q8	0K / 6.9 GB	14	2
Mpt 7B Instruct Q8	0K / 6.9 GB	18	2
Mpt 7B Q8	0K / 6.9 GB	14	1
Mpt 7B Storywriter 4bit 128g	0K / 3.9 GB	194	127
...writer 4bit 128g 65kTokens CPU	0K / 3.9 GB	15	9
Mpt 7B Chat	0K / 13.3 GB	80920	518
Mpt 7B Assistant	0K / 13.3 GB	11	1
Mpt 7B	0K / 13.3 GB	18460	1173
Mpt 7B Instruct	0K / 13.3 GB	7946	470

Note: green Score (e.g. "73.2") means that the model is better than 4bit/mpt-7b-storywriter-4bit-128g.