What are the hardware requirements for OrcaMaid V2 FIX 13B 32K?

OrcaMaid V2 FIX 13B 32K requires approximately 26 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 V2 FIX 13B 32K and how large is it?

OrcaMaid V2 FIX 13B 32K is developed by ddh0, 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 V2 FIX 13B 32K?

OrcaMaid V2 FIX 13B 32K is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

OrcaMaid V2 FIX 13B 32K by ddh0 — VRAM 26GB, 32K context

Name: OrcaMaid V2 FIX 13B 32K
Author: ddh0

OrcaMaid V2 FIX 13B 32K is an open-source language model by ddh0. Features: 13b LLM, VRAM: 26GB, Context: 32K, License: other, LLM Explorer Score: 0.1.

Custom code Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/ddh0/OrcaMaid-v2-FIX-13b-32k

OrcaMaid V2 FIX 13B 32K Parameters and Internals

Model Type

text generation

Additional Notes

Extended to 32768 context length via YaRN. Fixed version of OrcaMaid-v2-13b.

Training Details

Methodology:

Gradient SLERP merge, biased towards Orca

Context Length:

32768

Input Output

Input Format:

Alpaca prompt format for best results

Performance Tips:

Customize the system prompt to specific needs for best results

LLM Name	OrcaMaid V2 FIX 13B 32K
Repository 🤗	https://huggingface.co/ddh0/OrcaMaid-v2-FIX-13b-32k
Model Size	13b
Required VRAM	26 GB
Updated	2026-08-07
Maintainer	ddh0
Model Type	llama
Model Files	13.9 GB: 1-of-2 12.1 GB: 2-of-2
Model Architecture	LlamaForCausalLM
License	other
Context Length	32768
Model Max Length	32768
Transformers Version	4.36.1
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32000
Torch Data Type	float16

Rank the OrcaMaid V2 FIX 13B 32K 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

Quantized Models of the OrcaMaid V2 FIX 13B 32K

Model	Likes	Downloads	VRAM
OrcaMaid V2 FIX 13B 32K GGUF	5	646	5 GB
OrcaMaid V2 FIX 13B 32K GPTQ	4	12	7 GB
OrcaMaid V2 FIX 13B 32K AWQ	1	7	7 GB

Best Alternatives to OrcaMaid V2 FIX 13B 32K

Best Alternatives	Context / RAM	Downloads	Likes
Luminaura RP 13B	128K / 26 GB	9	1
Yarn Llama 2 13B 128K	128K / 26 GB	184	113
Agent Llama2 13B 80K	80K / 26.4 GB	5	0
Chat Llama2 13B 80K	80K / 52.8 GB	5	0
LongAlign 13B 64K	64K / 26 GB	96	13
LongAlign 13B 64K Base	64K / 26 GB	89	3
LongAlign 13B 64K	64K / 26 GB	11	13
LongAlign 13B 64K Base	64K / 26 GB	6	3
Openbuddy Llama2 13B V15p1 64K	64K / 26.1 GB	4	4
Openbuddy Llama2 13b64k V15	64K / 26.1 GB	12	2

Note: green Score (e.g. "73.2") means that the model is better than ddh0/OrcaMaid-v2-FIX-13b-32k.