What are the hardware requirements for Asclepius 13B GGML?

Asclepius 13B GGML requires approximately 5.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Asclepius 13B GGML and how large is it?

Asclepius 13B GGML is developed by TheBloke, a model with 13b 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 Asclepius 13B GGML?

Asclepius 13B GGML is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Asclepius 13B GGML by TheBloke — VRAM 5.5GB

Name: Asclepius 13B GGML
Author: TheBloke

Asclepius 13B GGML is an open-source language model by TheBloke. Features: 13b LLM, VRAM: 5.5GB, License: other, Quantized, LLM Explorer Score: 0.08.

Base model:finetune:starmpcc/a... Base model:starmpcc/asclepius-... Dataset:starmpcc/asclepius-syn... En Ggml Llama Medical Quantized Region:us

Model Card on HF 🤗: https://huggingface.co/TheBloke/Asclepius-13B-GGML

Asclepius 13B GGML Parameters and Internals

Model Type

Clinical LLM, Large Language Model, text2text-generation

Use Cases

Areas:

Named Entity Recognition, Abbreviation Expansion, Relation Extraction, Temporal Information Extraction, Coreference Resolution, Paraphrasing, Summarization, Question Answering

Primary Use Cases:

Perform 8 clinical NLP tasks with clinical notes

Limitations:

ONLY USE THIS MODEL FOR RESEARCH PURPOSE!!

Additional Notes

This model is the first publicly shareable clinical LLM, trained with synthetic data.

Supported Languages

English (NLP)

Training Details

Data Sources:

https://huggingface.co/datasets/starmpcc/Asclepius-Synthetic-Clinical-Notes

Methodology:

Initial training was conducted using causal language modeling on synthetic clinical notes. It was then fine-tuned with clinical instruction-response pairs.

Training Time:

Pre-Training (1 epoch): 1h 52m with 8x A100 80G; Instruction Fine-Tuning (3 epoch): 12h 16m with 8x A100 80G

Hardware Used:

8x A100 80G

LLM Name	Asclepius 13B GGML
Repository 🤗	https://huggingface.co/TheBloke/Asclepius-13B-GGML
Model Name	Asclepius 13B
Model Creator	Junu Kim
Base Model(s)	Asclepius 13B starmpcc/Asclepius-13B
Model Size	13b
Required VRAM	5.5 GB
Updated	2026-08-02
Maintainer	TheBloke
Model Type	llama
Model Files	5.5 GB 6.9 GB 6.3 GB 5.7 GB 7.4 GB 8.2 GB 7.9 GB 7.4 GB 9.0 GB 9.8 GB 9.2 GB 9.0 GB 10.7 GB 13.8 GB
Supported Languages	en
GGML Quantization	Yes
Quantization Type	ggml
Model Architecture	AutoModel
License	other

Rank the Asclepius 13B GGML 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 Asclepius 13B GGML

Best Alternatives	Context / RAM	Downloads	Likes
Llama 2 13B Chat GGML	0K / 5.5 GB	158	693
RuGPT 3.5 13B GGML	0K / 7.4 GB	10	8
RuGPT 3.5 13B GGML	0K / 7.4 GB	10	15
...penBuddy Llama2 13B V11.1 GGML	0K / 5.5 GB	11	5
...rca Platypus WizardLM 13B GGML	0K / 5.5 GB	6	6
Speechless Llama2 13B GGML	0K / 5.5 GB	4	2
Yarn Llama 2 13B 128K GGML	0K / 5.5 GB	5	6
Yarn Llama 2 13B 64K GGML	0K / 5.5 GB	7	5
Stheno L2 13B GGML	0K / 5.5 GB	7	5
UndiMix V2 13B GGML	0K / 5.5 GB	6	2

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Asclepius-13B-GGML.