What are the hardware requirements for Cerebras GPT 2.7B Alpaca SP?

Cerebras GPT 2.7B Alpaca SP requires approximately 5.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Cerebras GPT 2.7B Alpaca SP and how large is it?

Cerebras GPT 2.7B Alpaca SP is developed by lxe, a model with 2.7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Cerebras GPT 2.7B Alpaca SP perform on standard benchmarks?

Cerebras GPT 2.7B Alpaca SP has the following published scores: MMLU 25.12. Compare against reference models on this page or on the LLM Explorer leaderboards.

Cerebras GPT 2.7B Alpaca SP by lxe — VRAM 5.4GB

Name: Cerebras GPT 2.7B Alpaca SP
Author: lxe

Cerebras GPT 2.7B Alpaca SP is an open-source language model by lxe. Features: 2.7b LLM, VRAM: 5.4GB, License: apache-2.0, LLM Explorer Score: 0.11, Arc: 30.8, HellaSwag: 48.9, MMLU: 25.1, GSM8K: 0.5.

Code Endpoints compatible Gpt2 Pytorch Region:us

Model Card on HF 🤗: https://huggingface.co/lxe/Cerebras-GPT-2.7B-Alpaca-SP

Cerebras GPT 2.7B Alpaca SP Parameters and Internals

Model Type

text generation

Additional Notes

The model uses a shorter prompt structure and is designed for code-related tasks.

Training Details

Data Sources:

Alpaca dataset

Methodology:

Finetuned on a modified Alpaca dataset with a shorter prompt structure.

Model Architecture:

Cerebras-GPT architecture with a merged float16 model and LoRA

Input Output

Input Format:

Prompt starts with 'Human:' followed by the question and 'Assistant:' for the model's response.

Accepted Modalities:

text

Output Format:

Textual response as an answer to the prompts.

LLM Name	Cerebras GPT 2.7B Alpaca SP
Repository 🤗	https://huggingface.co/lxe/Cerebras-GPT-2.7B-Alpaca-SP
Model Size	2.7b
Required VRAM	5.4 GB
Updated	2026-08-06
Maintainer	lxe
Model Type	gpt2
Model Files	5.4 GB
Model Architecture	GPT2LMHeadModel
License	apache-2.0
Transformers Version	4.28.0.dev0
Vocabulary Size	50257
Torch Data Type	float16
Activation Function	gelu

Rank the Cerebras GPT 2.7B Alpaca SP 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 Cerebras GPT 2.7B Alpaca SP

Best Alternatives	Context / RAM	Downloads	Likes
Quokka 2.7B	0K / 5.4 GB	56	0

Note: green Score (e.g. "73.2") means that the model is better than lxe/Cerebras-GPT-2.7B-Alpaca-SP.