What are the hardware requirements for Orca2myth7.2 AWQ?

Orca2myth7.2 AWQ requires approximately 10.9 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 Orca2myth7.2 AWQ and how large is it?

Orca2myth7.2 AWQ is developed by TheBloke, a model with 20b 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 Orca2myth7.2 AWQ?

Orca2myth7.2 AWQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Orca2myth7.2 AWQ by TheBloke — VRAM 10.9GB, 4K context

Name: Orca2myth7.2 AWQ
Author: TheBloke

Orca2myth7.2 AWQ is an open-source language model by TheBloke. Features: 20b LLM, VRAM: 10.9GB, Context: 4K, License: other, Quantized, LLM Explorer Score: 0.1.

4-bit Awq Base model:quantized:thebigble... Base model:thebigblender/orca2... Llama Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/TheBloke/Orca2myth7.2-AWQ

Orca2myth7.2 AWQ Parameters and Internals

Model Type

llama

Additional Notes

The model was quantized using hardware provided by Massed Compute. AWQ supports efficient, low-bit weight quantization enhancing Transformer-based inference speed and quality.

Training Details

Data Sources:

VMware Open Instruct

Methodology:

Float16 quantization, AWQ (4-bit quantization)

Context Length:

4096

Hardware Used:

Massed Compute

Model Architecture:

A merge of Orca2flat and PygmalionAI/mythalion-13b using specific layer ranges and merge methods.

Input Output

Input Format:

{prompt}

LLM Name	Orca2myth7.2 AWQ
Repository 🤗	https://huggingface.co/TheBloke/Orca2myth7.2-AWQ
Model Name	Orca2Myth7.2
Model Creator	The Big Blender
Base Model(s)	TheBigBlender/Orca2myth7.2 TheBigBlender/Orca2myth7.2
Model Size	20b
Required VRAM	10.9 GB
Updated	2026-08-07
Maintainer	TheBloke
Model Type	llama
Model Files	10.0 GB: 1-of-2 0.9 GB: 2-of-2
AWQ Quantization	Yes
Quantization Type	awq
Model Architecture	LlamaForCausalLM
License	other
Context Length	4096
Model Max Length	4096
Transformers Version	4.35.2
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32000
Torch Data Type	float16

Rank the Orca2myth7.2 AWQ 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 Orca2myth7.2 AWQ

Best Alternatives	Context / RAM	Downloads	Likes
Norocetacean 20B 10K AWQ	10K / 10.9 GB	11	2
DaringMaid 20B AWQ	4K / 10.9 GB	2	2
Rose Kimiko 20B AWQ	4K / 10.9 GB	0	1
Nethena 20B Glued AWQ	4K / 10.9 GB	4	2
Iambe Storyteller 20B AWQ	4K / 10.9 GB	7	1
Iambe 20B DARE AWQ	4K / 10.9 GB	3	1
Noromaid 20B V0.1.1 AWQ	4K / 10.9 GB	5	4
Rose 20B AWQ	4K / 10.9 GB	1	1
Nethena 20B AWQ	4K / 10.9 GB	8	2
MXLewd L2 20B AWQ	4K / 10.9 GB	9	3