What are the hardware requirements for OrcaMaid V3 13B 32K 8.0bpw H8 EXL2?

OrcaMaid V3 13B 32K 8.0bpw H8 EXL2 requires approximately 13.2 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed OrcaMaid V3 13B 32K 8.0bpw H8 EXL2 and how large is it?

OrcaMaid V3 13B 32K 8.0bpw H8 EXL2 is developed by LoneStriker, 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 OrcaMaid V3 13B 32K 8.0bpw H8 EXL2?

OrcaMaid V3 13B 32K 8.0bpw H8 EXL2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

OrcaMaid V3 13B 32K 8.0bpw H8 EXL2 by LoneStriker — VRAM 13.2GB, 32K context

Name: OrcaMaid V3 13B 32K 8.0bpw H8 EXL2
Author: LoneStriker

OrcaMaid V3 13B 32K 8.0bpw H8 EXL2 is an open-source language model by LoneStriker. Features: 13b LLM, VRAM: 13.2GB, Context: 32K, License: other, Quantized, Merged, LLM Explorer Score: 0.1.

Merged Model Custom code Endpoints compatible Exl2 Llama Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/LoneStriker/OrcaMaid-v3-13b-32k-8.0bpw-h8-exl2

OrcaMaid V3 13B 32K 8.0bpw H8 EXL2 Parameters and Internals

Model Type

text generation

Additional Notes

This is the third version of OrcaMaid, a weighted gradient SLERP merge aimed at creating an intelligent and human-like model, especially for role-playing (RP).

Input Output

Input Format:

Alpaca prompt format

Performance Tips:

Customize the system prompt to your specific needs for best results.

LLM Name	OrcaMaid V3 13B 32K 8.0bpw H8 EXL2
Repository 🤗	https://huggingface.co/LoneStriker/OrcaMaid-v3-13b-32k-8.0bpw-h8-exl2
Merged Model	Yes
Model Size	13b
Required VRAM	13.2 GB
Updated	2026-08-08
Maintainer	LoneStriker
Model Type	llama
Model Files	8.6 GB: 1-of-2 4.6 GB: 2-of-2
Quantization Type	exl2
Model Architecture	LlamaForCausalLM
License	other
Context Length	32768
Model Max Length	32768
Transformers Version	4.36.2
Tokenizer Class	LlamaTokenizer
Padding Token	[PAD]
Vocabulary Size	32000
Torch Data Type	float16

Rank the OrcaMaid V3 13B 32K 8.0bpw H8 EXL2 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 OrcaMaid V3 13B 32K 8.0bpw H8 EXL2

Best Alternatives	Context / RAM	Downloads	Likes
Llama13b 32K Illumeet Finetune	32K / 26 GB	5	0
...Maid V3 13B 32K 6.0bpw H6 EXL2	32K / 10 GB	5	1
WhiteRabbitNeo 13B V1	16K / 26 GB	3146	453
CodeLlama 13B Python Fp16	16K / 26 GB	121	25
CodeLlama 13B Fp16	16K / 26 GB	9	67
CodeLlama 13B Instruct Fp16	16K / 26 GB	137	28
Codellama 13B Bnb 4bit	16K / 7.2 GB	129	5
...Llama 13B Instruct Hf 4bit MLX	16K / 7.8 GB	113	3
WhiteRabbitNeo 13B V1 4bit Mlx	16K / 7.8 GB	147	2
Trinity 13B	16K / 26 GB	14	15

Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/OrcaMaid-v3-13b-32k-8.0bpw-h8-exl2.