What are the hardware requirements for Slim Xsum?

Slim Xsum requires approximately 5.6 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 Slim Xsum and how large is it?

Slim Xsum is developed by llmware, 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 Slim Xsum?

Slim Xsum is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Slim Xsum by llmware — VRAM 5.6GB, 4K context

Name: Slim Xsum
Author: llmware

Slim Xsum is an open-source language model by llmware. Features: 3b LLM, VRAM: 5.6GB, Context: 4K, License: cc-by-sa-4.0, LLM Explorer Score: 0.11.

Custom code Pytorch Region:us Stablelm epoch

Model Card on HF 🤗: https://huggingface.co/llmware/slim-xsum

Slim Xsum Parameters and Internals

Model Type

extreme summarization

Additional Notes

SLIMs intend to provide a middle-ground between encoder-based classifiers and open-ended API-based LLMs, aiming for intuitive, flexible language responses.

Training Details

Data Volume:

100 million unique examples

Methodology:

Fine-tuning of stablelm model, utilizing synthetic data generation termed 'symbolic deduction and traceback'.

Input Output

Input Format:

function = "classify" params = "xsum" prompt = " " + {text} + "\n" + '<{function}> ' + {params} + "" + "\n:"

Accepted Modalities:

text

Output Format:

{'xsum': ['This is a short text summary or headline.']}

LLM Name	Slim Xsum
Repository 🤗	https://huggingface.co/llmware/slim-xsum
Model Size	3b
Required VRAM	5.6 GB
Updated	2026-08-07
Maintainer	llmware
Model Type	stablelm_epoch
Model Files	5.6 GB
Model Architecture	StableLMEpochForCausalLM
License	cc-by-sa-4.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.33.2
Tokenizer Class	GPTNeoXTokenizer
Vocabulary Size	50304
Torch Data Type	bfloat16

Rank the Slim Xsum 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 Slim Xsum

Best Alternatives	Context / RAM	Downloads	Likes
Stable Code 3B Mlx	16K / 5.6 GB	17	1
Aura 3B	4K / 5.6 GB	3	2
Slim Extract	4K / 5.6 GB	10	13
Slim Boolean	4K / 5.6 GB	9	4
Slim Sa Ner	4K / 5.6 GB	20	6
Slim Tags 3B	4K / 5.6 GB	11	4
Slim Summary	4K / 5.6 GB	10	8
Tofu 3B	4K / 5.6 GB	5	2
Memphis CoT 3B	4K / 5.6 GB	24	31
Fett Uccine Mini 3B	4K / 5.6 GB	6	3

Note: green Score (e.g. "73.2") means that the model is better than llmware/slim-xsum.