What are the hardware requirements for Mpt 7B Storywriter Q8?

Mpt 7B Storywriter Q8 requires approximately 6.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Mpt 7B Storywriter Q8 and how large is it?

Mpt 7B Storywriter Q8 is developed by Abzu, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Mpt 7B Storywriter Q8 perform on standard benchmarks?

Mpt 7B Storywriter Q8 has the following published scores: MMLU 28.8. Compare against reference models on this page or on the LLM Explorer leaderboards.

Mpt 7B Storywriter Q8 by Abzu — VRAM 6.9GB

Name: Mpt 7B Storywriter Q8
Author: Abzu

Mpt 7B Storywriter Q8 is an open-source language model by Abzu. Features: 7b LLM, VRAM: 6.9GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.11, Arc: 45.7, HellaSwag: 74.1, MMLU: 28.8.

Arxiv:2108.12409 Arxiv:2205.14135 Arxiv:2302.06675 8-bit Composer Custom code Dataset:the pile books3 Llm-foundry Mosaicml Mpt Q8 Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/Abzu/mpt-7b-storywriter-q8

Mpt 7B Storywriter Q8 Parameters and Internals

Model Type

text generation

Use Cases

Areas:

Fictional story generation

Limitations:

Can produce factually incorrect output, Model could generate lewd, biased or otherwise offensive outputs

Additional Notes

MPT-7B-StoryWriter-65k+ uses ALiBi to allow context length extrapolation beyond 65k tokens.

Training Details

Data Sources:

the_pile_books3

Methodology:

finetuning

Context Length:

65536

Training Time:

2 days

Hardware Used:

8 A100-80GB GPUs

Model Architecture:

Modified decoder-only transformer with FlashAttention and ALiBi

Responsible Ai Considerations

Fairness:

Model may produce biased outputs.

LLM Name	Mpt 7B Storywriter Q8
Repository 🤗	https://huggingface.co/Abzu/mpt-7b-storywriter-q8
Base Model(s)	Mpt 7B Storywriter Qlora Jordancole21/mpt-7b-storywriter-qlora
Model Size	7b
Required VRAM	6.9 GB
Updated	2026-08-25
Maintainer	Abzu
Model Type	mpt
Model Files	6.9 GB
Quantization Type	q8
Model Architecture	MPTForCausalLM
License	apache-2.0
Model Max Length	65536
Transformers Version	4.30.2
Tokenizer Class	GPTNeoXTokenizer
Vocabulary Size	50432
Torch Data Type	bfloat16

Rank the Mpt 7B Storywriter Q8 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 Q8

Best Alternatives	Context / RAM	Downloads	Likes
Mpt 7B Chat Q8	0K / 6.9 GB	17	1
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 Storywriter 4bit 128g	0K / 3.9 GB	23	20
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 Abzu/mpt-7b-storywriter-q8.