What are the hardware requirements for Shears Mpt 7B 50 Base?

Shears Mpt 7B 50 Base requires approximately 13.3 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Shears Mpt 7B 50 Base and how large is it?

Shears Mpt 7B 50 Base is developed by IntelLabs, 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 Shears Mpt 7B 50 Base?

Shears Mpt 7B 50 Base is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Shears Mpt 7B 50 Base by IntelLabs — VRAM 13.3GB

Name: Shears Mpt 7B 50 Base
Author: IntelLabs

Shears Mpt 7B 50 Base is an open-source language model by IntelLabs. Features: 7b LLM, VRAM: 13.3GB, License: apache-2.0, LLM Explorer Score: 0.12.

Arxiv:2306.11695 Arxiv:2404.10934 Arxiv:2501.16372 Custom code En Endpoints compatible Mpt Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/IntelLabs/shears-mpt-7b-50-base

Shears Mpt 7B 50 Base Parameters and Internals

Additional Notes

The model is a sparsified version of the MPT-7B with 50% sparsity used as a base model in Shears.

LLM Name	Shears Mpt 7B 50 Base
Repository 🤗	https://huggingface.co/IntelLabs/shears-mpt-7b-50-base
Model Size	7b
Required VRAM	13.3 GB
Updated	2026-07-31
Maintainer	IntelLabs
Model Type	mpt
Model Files	9.9 GB: 1-of-2 3.4 GB: 2-of-2
Supported Languages	en
Model Architecture	MPTForCausalLM
License	apache-2.0
Model Max Length	2048
Transformers Version	4.31.0
Tokenizer Class	GPTNeoXTokenizer
Vocabulary Size	50432
Torch Data Type	float16

Rank the Shears Mpt 7B 50 Base 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 Shears Mpt 7B 50 Base

Best Alternatives	Context / RAM	Downloads	Likes
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
Mpt 7B Storywriter	0K / 13.3 GB	2261	839
Mpt 7B Int8 Ov	0K / 0 GB	13	0
Mpt 7B	0K / 26.5 GB	3064	1
Mpt 7B 8K	0K / 13.3 GB	1915	26
Mpt 7B 8K Chat	0K / 13.3 GB	1942	40
Mpt 7B 8K Instruct	0K / 13.3 GB	2012	27

Note: green Score (e.g. "73.2") means that the model is better than IntelLabs/shears-mpt-7b-50-base.